Xiaoming Zhai

Yun Wang, Xin Xia, Xuansheng Wu et al.

LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through evaluation heuristics developed over extensive practice. We ask whether LLMs can learn similar heuristics directly from scoring experience, and formalize this as the concept of assessment skills: item-independent natural-language procedural knowledge that guides LLMs through specific stages of the scoring workflow. Focusing on rubric construction as a first instantiation, we propose an iterative framework that decomposes a skill into a fixed scaffold and learnable item-agnostic rules, refining the rules through LLM-driven diagnosis of scoring errors and validation-gated selection. The framework requires no expert-written rubric. On all ten ASAP-SAS items, optimized skills substantially improve LLM-based scoring and frequently surpass the dataset-provided expert rubric. Cross-item transfer experiments further reveal that learned skills capture both generalizable and item-specific patterns.

Tianyang Zhong, Zhengliang Liu, Yi Pan et al.

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.

Ehsan Latif, Gengchen Mai, Matthew Nyaaba et al.

Artificial general intelligence (AGI) has gained global recognition as a future technology due to the emergence of breakthrough large language models and chatbots such as GPT-4 and ChatGPT, respectively. Compared to conventional AI models, typically designed for a limited range of tasks, demand significant amounts of domain-specific data for training and may not always consider intricate interpersonal dynamics in education. AGI, driven by the recent large pre-trained models, represents a significant leap in the capability of machines to perform tasks that require human-level intelligence, such as reasoning, problem-solving, decision-making, and even understanding human emotions and social interactions. This position paper reviews AGI's key concepts, capabilities, scope, and potential within future education, including achieving future educational goals, designing pedagogy and curriculum, and performing assessments. It highlights that AGI can significantly improve intelligent tutoring systems, educational assessment, and evaluation procedures. AGI systems can adapt to individual student needs, offering tailored learning experiences. They can also provide comprehensive feedback on student performance and dynamically adjust teaching methods based on student progress. The paper emphasizes that AGI's capabilities extend to understanding human emotions and social interactions, which are critical in educational settings. The paper discusses that ethical issues in education with AGI include data bias, fairness, and privacy and emphasizes the need for codes of conduct to ensure responsible AGI use in academic settings like homework, teaching, and recruitment. We also conclude that the development of AGI necessitates interdisciplinary collaborations between educators and AI engineers to advance research and application efforts.

Xiaoming Zhai, Joseph Krajcik

Pseudo Artificial Intelligence bias (PAIB) is broadly disseminated in the literature, which can result in unnecessary AI fear in society, exacerbate the enduring inequities and disparities in access to and sharing the benefits of AI applications, and waste social capital invested in AI research. This study systematically reviews publications in the literature to present three types of PAIBs identified due to: a) misunderstandings, b) pseudo mechanical bias, and c) over-expectations. We discussed the consequences of and solutions to PAIBs, including certifying users for AI applications to mitigate AI fears, providing customized user guidance for AI applications, and developing systematic approaches to monitor bias. We concluded that PAIB due to misunderstandings, pseudo mechanical bias, and over-expectations of algorithmic predictions is socially harmful.

Xuansheng Wu, Xinyu He, Tianming Liu et al.

Developing models to automatically score students' written responses to science problems is critical for science education. However, collecting and labeling sufficient student responses for training models is time and cost-consuming. Recent studies suggest that pre-trained language models can be adapted to downstream tasks without fine-tuning with prompts. However, no research has employed such a prompt approach in science education. As student responses are presented with natural language, aligning the scoring procedure as the next sentence prediction task using prompts can skip the costly fine-tuning stage. In this study, we developed a zero-shot approach to automatically score student responses via Matching Exemplars as Next Sentence Prediction (MeNSP). This approach employs no training samples. We first apply MeNSP in scoring three assessment tasks of scientific argumentation and found machine-human scoring agreements, Cohen's Kappa ranges from 0.30 to 0.57, and F1 score ranges from 0.54 to 0.81. To improve the performance, we extend our research to the few-shots setting, either randomly selecting labeled student responses or manually constructing responses to fine-tune the models. We find that one task's performance is improved with more samples, Cohen's Kappa from 0.30 to 0.38, and F1 score from 0.54 to 0.59; for the two others, scoring performance is not improved. We also find that randomly selected few-shots perform better than the human expert-crafted approach. This study suggests that MeNSP can yield referable automatic scoring for student responses while significantly reducing the cost of model training. This method can benefit low-stakes classroom assessment practices in science education. Future research should further explore the applicability of the MeNSP in different types of assessment tasks in science education and improve the model performance.

Ehsan Latif, Xiaoming Zhai

This study highlights the potential of fine-tuned ChatGPT (GPT-3.5) for automatically scoring student written constructed responses using example assessment tasks in science education. Recent studies on OpenAI's generative model GPT-3.5 proved its superiority in predicting the natural language with high accuracy and human-like responses. GPT-3.5 has been trained over enormous online language materials such as journals and Wikipedia; therefore, more than direct usage of pre-trained GPT-3.5 is required for automatic scoring as students utilize a different language than trained material. These imply that a domain-specific model, fine-tuned over data for specific tasks, can enhance model performance. In this study, we fine-tuned GPT-3.5 on six assessment tasks with a diverse dataset of middle-school and high-school student responses and expert scoring. The six tasks comprise two multi-label and four multi-class assessment tasks. We compare the performance of fine-tuned GPT-3.5 with the fine-tuned state-of-the-art Google's generated language model, BERT. The results show that in-domain training corpora constructed from science questions and responses for BERT achieved average accuracy = 0.838, SD = 0.069. GPT-3.5 shows a remarkable average increase (9.1%) in automatic scoring accuracy (mean = 9.15, SD = 0.042) for the six tasks, p =0.001 < 0.05. Specifically, for multi-label tasks (item 1 with 5 labels; item 2 with 10 labels), GPT-3.5 achieved significantly higher scoring accuracy than BERT across all the labels, with the second item achieving a 7.1% increase. The average scoring increase for the four multi-class items for GPT-3.5 was 10.6% compared to BERT. Our study confirmed the effectiveness of fine-tuned GPT-3.5 for automatic scoring of student responses on domain-specific data in education with high accuracy. We have released fine-tuned models for public use and community engagement.

Gyeong-Geon Lee, Ehsan Latif, Xuansheng Wu et al.

This study investigates the application of large language models (LLMs), specifically GPT-3.5 and GPT-4, with Chain-of-Though (CoT) in the automatic scoring of student-written responses to science assessments. We focused on overcoming the challenges of accessibility, technical complexity, and lack of explainability that have previously limited the use of artificial intelligence-based automatic scoring tools among researchers and educators. With a testing dataset comprising six assessment tasks (three binomial and three trinomial) with 1,650 student responses, we employed six prompt engineering strategies to automatically score student responses. The six strategies combined zero-shot or few-shot learning with CoT, either alone or alongside item stem and scoring rubrics. Results indicated that few-shot (acc = .67) outperformed zero-shot learning (acc = .60), with 12.6% increase. CoT, when used without item stem and scoring rubrics, did not significantly affect scoring accuracy (acc = .60). However, CoT prompting paired with contextual item stems and rubrics proved to be a significant contributor to scoring accuracy (13.44% increase for zero-shot; 3.7% increase for few-shot). We found a more balanced accuracy across different proficiency categories when CoT was used with a scoring rubric, highlighting the importance of domain-specific reasoning in enhancing the effectiveness of LLMs in scoring tasks. We also found that GPT-4 demonstrated superior performance over GPT -3.5 in various scoring tasks when combined with the single-call greedy sampling or ensemble voting nucleus sampling strategy, showing 8.64% difference. Particularly, the single-call greedy sampling strategy with GPT-4 outperformed other approaches.

Zhengliang Liu, Xinyu He, Lei Liu et al.

This study aims at improving the performance of scoring student responses in science education automatically. BERT-based language models have shown significant superiority over traditional NLP models in various language-related tasks. However, science writing of students, including argumentation and explanation, is domain-specific. In addition, the language used by students is different from the language in journals and Wikipedia, which are training sources of BERT and its existing variants. All these suggest that a domain-specific model pre-trained using science education data may improve model performance. However, the ideal type of data to contextualize pre-trained language model and improve the performance in automatically scoring student written responses remains unclear. Therefore, we employ different data in this study to contextualize both BERT and SciBERT models and compare their performance on automatic scoring of assessment tasks for scientific argumentation. We use three datasets to pre-train the model: 1) journal articles in science education, 2) a large dataset of students' written responses (sample size over 50,000), and 3) a small dataset of students' written responses of scientific argumentation tasks. Our experimental results show that in-domain training corpora constructed from science questions and responses improve language model performance on a wide variety of downstream tasks. Our study confirms the effectiveness of continual pre-training on domain-specific data in the education domain and demonstrates a generalizable strategy for automating science education tasks with high accuracy. We plan to release our data and SciEdBERT models for public use and community engagement.

Xuansheng Wu, Padmaja Pravin Saraf, Gyeonggeon Lee et al.

Large language models (LLMs) have demonstrated strong potential in performing automatic scoring for constructed response assessments. While constructed responses graded by humans are usually based on given grading rubrics, the methods by which LLMs assign scores remain largely unclear. It is also uncertain how closely AI's scoring process mirrors that of humans or if it adheres to the same grading criteria. To address this gap, this paper uncovers the grading rubrics that LLMs used to score students' written responses to science tasks and their alignment with human scores. We also examine whether enhancing the alignments can improve scoring accuracy. Specifically, we prompt LLMs to generate analytic rubrics that they use to assign scores and study the alignment gap with human grading rubrics. Based on a series of experiments with various configurations of LLM settings, we reveal a notable alignment gap between human and LLM graders. While LLMs can adapt quickly to scoring tasks, they often resort to shortcuts, bypassing deeper logical reasoning expected in human grading. We found that incorporating high-quality analytical rubrics designed to reflect human grading logic can mitigate this gap and enhance LLMs' scoring accuracy. These results underscore the need for a nuanced approach when applying LLMs in science education and highlight the importance of aligning LLM outputs with human expectations to ensure efficient and accurate automatic scoring.

Luyang Fang, Gyeong-Geon Lee, Xiaoming Zhai

Machine learning-based automatic scoring faces challenges with unbalanced student responses across scoring categories. To address this, we introduce a novel text data augmentation framework leveraging GPT-4, a generative large language model, specifically tailored for unbalanced datasets in automatic scoring. Our experimental dataset comprised student written responses to four science items. We crafted prompts for GPT-4 to generate responses, especially for minority scoring classes, enhancing the data set. We then finetuned DistillBERT for automatic scoring based on the augmented and original datasets. Model performance was assessed using accuracy, precision, recall, and F1 metrics. Our findings revealed that incorporating GPT-4-augmented data remarkedly improved model performance, particularly for precision and F1 scores. Interestingly, the extent of improvement varied depending on the specific dataset and the proportion of augmented data used. Notably, we found that a varying amount of augmented data (20%-40%) was needed to obtain stable improvement for automatic scoring. Comparisons with models trained on additional student-written responses suggest that GPT-4 augmented models match those trained with student data. This research underscores the potential and effectiveness of data augmentation techniques utilizing generative large language models like GPT-4 in addressing unbalanced datasets within automated assessment.

Gyeong-Geon Lee, Xiaoming Zhai

Scoring student-drawn models is time-consuming. Recently released GPT-4V provides a unique opportunity to advance scientific modeling practices by leveraging the powerful image processing capability. To test this ability specifically for automatic scoring, we developed a method NERIF (Notation-Enhanced Rubric Instruction for Few-shot Learning) employing instructional note and rubrics to prompt GPT-4V to score students' drawn models for science phenomena. We randomly selected a set of balanced data (N = 900) that includes student-drawn models for six modeling assessment tasks. Each model received a score from GPT-4V ranging at three levels: 'Beginning,' 'Developing,' or 'Proficient' according to scoring rubrics. GPT-4V scores were compared with human experts' scores to calculate scoring accuracy. Results show that GPT-4V's average scoring accuracy was mean =.51, SD = .037. Specifically, average scoring accuracy was .64 for the 'Beginning' class, .62 for the 'Developing' class, and .26 for the 'Proficient' class, indicating that more proficient models are more challenging to score. Further qualitative study reveals how GPT-4V retrieves information from image input, including problem context, example evaluations provided by human coders, and students' drawing models. We also uncovered how GPT-4V catches the characteristics of student-drawn models and narrates them in natural language. At last, we demonstrated how GPT-4V assigns scores to student-drawn models according to the given scoring rubric and instructional notes. Our findings suggest that the NERIF is an effective approach for employing GPT-4V to score drawn models. Even though there is space for GPT-4V to improve scoring accuracy, some mis-assigned scores seemed interpretable to experts. The results of this study show that utilizing GPT-4V for automatic scoring of student-drawn models is promising.

Yizhu Gao, Zhongzhou Chen, Min Li et al.

Generative Artificial Intelligence (GenAI) presents a governance challenge for STEM assessment. Unrestricted GenAI access enables task outsourcing that undermines the validity of traditional assessments; blanket prohibitions are difficult to enforce, may push use underground, and do little to prepare students for workplaces where GenAI-supported workflows are increasingly common. This paper addresses this dilemma by proposing a framework grounded in Evidence-Centered Design (ECD) that treats GenAI as a design variable within the assessment argument rather than an external threat to it. The framework analyzes how GenAI reshapes the student model, evidence model, and task model, and uses this analysis to articulate three principled governance stances. Restrict is warranted when GenAI would contaminate the inferential link between student work products and targeted unaided proficiency. Scaffold is warranted when bounded GenAI support can support peripheral demands without revealing the target construct, preserving inferential interpretability. Require is warranted when the target construct is disciplinary AI interaction competency and tasks can be designed to elicit process artifacts, including prompts, critiques, and revisions, that make student reasoning observable, scorable, and distinguishable from AI-generated output. This framework specifies when to restrict, scaffold, or require GenAI use in STEM assessment. We present two task designs deployed in an introductory physics course and demonstrate that disciplinary AI interaction competencies are observable in student response artifacts and can be scored using defensible rubrics grounded in student data and expert knowledge. By situating GenAI governance within validity arguments, the framework offers actionable guidance for preserving learning integrity while supporting authentic preparation for AI-enabled professional environments.

Chen Cao, Zijian Ding, Gyeong-Geon Lee et al.

This study explores the integration of generative artificial intelligence (AI), specifically large language models, with multi-modal analogical reasoning as an innovative approach to enhance science, technology, engineering, and mathematics (STEM) education. We have developed a novel system that utilizes the capacities of generative AI to transform intricate principles in mathematics, physics, and programming into comprehensible metaphors. To further augment the educational experience, these metaphors are subsequently converted into visual form. Our study aims to enhance the learners' understanding of STEM concepts and their learning engagement by using the visual metaphors. We examine the efficacy of our system via a randomized A/B/C test, assessing learning gains and motivation shifts among the learners. Our study demonstrates the potential of applying large language models to educational practice on STEM subjects. The results will shed light on the design of educational system in terms of harnessing AI's potential to empower educational stakeholders.

Xuansheng Wu, Haiyan Zhao, Yaochen Zhu et al.

Explainable AI (XAI) refers to techniques that provide human-understandable insights into the workings of AI models. Recently, the focus of XAI is being extended toward explaining Large Language Models (LLMs). This extension calls for a significant transformation in the XAI methodologies for two reasons. First, many existing XAI methods cannot be directly applied to LLMs due to their complexity and advanced capabilities. Second, as LLMs are increasingly deployed in diverse applications, the role of XAI shifts from merely opening the ``black box'' to actively enhancing the productivity and applicability of LLMs in real-world settings. Meanwhile, the conversation and generation abilities of LLMs can reciprocally enhance XAI. Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can explain and improve LLM-based AI systems and (2) how XAI techniques can be improved by using LLMs. We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges. We also provide case studies to demonstrate how to obtain and leverage explanations. The code used in this paper can be found at: https://github.com/JacksonWuxs/UsableXAI_LLM.

Qitao Tan, Xiaoying Song, Arman Akbari et al.

Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but legitimate for authorized professionals, limiting helpfulness in specialized professional settings. Existing approaches either require costly realignment or rely on inference-time steering that suffers from imprecise control and added latency. To this end, we propose \textsc{Palette}, a modular, controllable, and efficient framework that selectively relaxes refusal behavior on authorized target domains while preserving standard safety elsewhere. Our method identifies a refusal direction via multi-objective search and internalizes it into the model through lightweight adaptation. \textsc{Palette} further supports modular composition: it learns domain-specific safety controls independently and composes them through parameter merging, enabling on-demand multi-domain authorization without retraining. Experiments across four safety benchmarks, multiple model variants, and both LLMs and VLMs show that \textsc{Palette} delivers precise safety control without sacrificing general utility, offering a practical path toward foundation models that adapt to diverse professional needs.

Xuansheng Wu, Jiayi Yuan, Wenlin Yao et al.

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures, and refining their capabilities. Although sparse autoencoders (SAEs) have shown promise for interpreting LLM internal representations, limited research has explored how to better explain SAE features, i.e., understanding the semantic meaning of features learned by SAE. Our theoretical analysis reveals that existing explanation methods suffer from the frequency bias issue, where they emphasize linguistic patterns over semantic concepts, while the latter is more critical to steer LLM behaviors. To address this, we propose using a fixed vocabulary set for feature interpretations and designing a mutual information-based objective, aiming to better capture the semantic meaning behind these features. We further propose two runtime steering strategies that adjust the learned feature activations based on their corresponding explanations. Empirical results show that, compared to baselines, our method provides more discourse-level explanations and effectively steers LLM behaviors to defend against jailbreak attacks. These findings highlight the value of explanations for steering LLM behaviors in downstream applications. We will release our code and data once accepted.

Xiaoming Zhai

Generative AI (GenAI) has rapidly entered education, yet its user experience is often explained through adoption-oriented constructs such as usefulness, ease of use, and engagement. We argue that these constructs are no longer sufficient because systems such as ChatGPT do not merely support learning tasks but also participate in knowledge construction. Existing theories cannot explain why GenAI frequently produces experiences characterized by negotiated authority, redistributed cognition, and accountability tension. To address this gap, this paper develops the Human--AI Epistemic Partnership Theory (HAEPT), explaining the GenAI user experience as a form of epistemic partnership that features a dynamic negotiation of three interlocking contracts: epistemic, agency, and accountability. We argue that findings on trust, over-reliance, academic integrity, teacher caution, and relational interaction about GenAI can be reinterpreted as tensions within these contracts rather than as isolated issues. Instead of holding a single, stable view of GenAI, users adjust how they relate to it over time through calibration cycles. These repeated interactions account for why trust and skepticism often coexist and for how partnership modes describe recurrent configurations of human--AI collaboration across tasks. To demonstrate the usefulness of HAEPT, we applied it to analyze the UX of collaborative learning with AI speakers and AI-facilitated scientific argumentation, illustrating different contract configurations.

Ying Zhang, Ningxi Cheng, Yizhu Gao et al.

Q-matrices are a cornerstone of theory-driven assessment and learning analytics, making item demands and students' underlying knowledge components and misconceptions explicit and actionable. However, Q-matrices are typically crafted by experts, making them time-consuming to build, prone to subjectivity, and difficult to validate empirically. We propose a framework for human-AI Q-matrix refinement in which large language models (LLMs) generate candidate Q-matrices using structured, misconception-aware prompting, and NeuralCDM provides an empirical evaluation layer to compare candidates based on how well they explain student response data. We apply the framework to a thermodynamics assessment dataset and benchmark locally deployed LLMs against cloud-served models. Results show that iteratively refined LLM-generated Q-matrices can exceed expert-baseline model fit (AUC 0.780 vs. 0.717), and that locally deployed models achieve comparable performance to cloud APIs, supporting privacy-preserving deployment.

Xuansheng Wu, Wenhao Yu, Xiaoming Zhai et al.

Modern text classification methods heavily rely on contextual embeddings from large language models (LLMs). Compared to human-engineered features, these embeddings provide automatic and effective representations for classification model training. However, they also introduce a challenge: we lose the ability to manually remove unintended features, such as sensitive or task-irrelevant features, to guarantee regulatory compliance or improve the generalizability of classification models. This limitation arises because LLM embeddings are opaque and difficult to interpret. In this paper, we propose a novel framework to identify and regularize unintended features in the LLM latent space. Specifically, we first pre-train a sparse autoencoder (SAE) to extract interpretable features from LLM latent spaces. To ensure the SAE can capture task-specific features, we further fine-tune it on task-specific datasets. In training the classification model, we propose a simple and effective regularizer, by minimizing the similarity between the classifier weights and the identified unintended feature, to remove the impact of these unintended features on classification. We evaluate the proposed framework on three real-world tasks, including toxic chat detection, reward modeling, and disease diagnosis. Results show that the proposed self-regularization framework can improve the classifier's generalizability by regularizing those features that are not semantically correlated to the task. This work pioneers controllable text classification on LLM latent spaces by leveraging interpreted features to address generalizability, fairness, and privacy challenges. The code and data are publicly available at https://github.com/JacksonWuxs/Controllable_LLM_Classifier.

Qitao Tan, Xiaoying Song, Ningxi Cheng et al.

Public large language models (LLMs) are typically safety-aligned during pretraining, yet task-specific fine-tuning required for deployment often erodes this alignment and introduces safety risks. Existing defenses either embed safety recovery into fine-tuning or rely on fine-tuning-derived priors for post-hoc correction, leaving safety recovery tightly coupled with training and incurring high computational overhead and a complex workflow. To address these challenges, we propose \texttt{Q-realign}, a post-hoc defense method based on post-training quantization, guided by an analysis of representational structure. By reframing quantization as a dual-objective procedure for compression and safety, \texttt{Q-realign} decouples safety alignment from fine-tuning and naturally piggybacks into modern deployment pipelines. Experiments across multiple models and datasets demonstrate that our method substantially reduces unsafe behaviors while preserving task performance, with significant reductions in memory usage and GPU hours. Notably, our approach can recover the safety alignment of a fine-tuned 7B LLM on a single RTX 4090 within 40 minutes. Overall, our work provides a practical, turnkey solution for safety-aware deployment.

Xin Xia, Nejla Yuruk, Yun Wang et al.

Generative artificial intelligence (AI) offers scalable support for formative feedback, yet most AI-generated feedback relies on task-specific rubrics authored by domain experts. While effective, rubric authoring is time-consuming and limits scalability across instructional contexts. Learning progressions (LP) provide a theoretically grounded representation of students' developing understanding and may offer an alternative solution. This study examines whether an LP-driven rubric generation pipeline can produce AI-generated feedback comparable in quality to feedback guided by expert-authored task rubrics. We analyzed AI-generated feedback for written scientific explanations produced by 207 middle school students in a chemistry task. Two pipelines were compared: (a) feedback guided by a human expert-designed, task-specific rubric, and (b) feedback guided by a task-specific rubric automatically derived from a learning progression prior to grading and feedback generation. Two human coders evaluated feedback quality using a multi-dimensional rubric assessing Clarity, Accuracy, Relevance, Engagement and Motivation, and Reflectiveness (10 sub-dimensions). Inter-rater reliability was high, with percent agreement ranging from 89% to 100% and Cohen's kappa values for estimable dimensions (kappa = .66 to .88). Paired t-tests revealed no statistically significant differences between the two pipelines for Clarity (t1 = 0.00, p1 = 1.000; t2 = 0.84, p2 = .399), Relevance (t1 = 0.28, p1 = .782; t2 = -0.58, p2 = .565), Engagement and Motivation (t1 = 0.50, p1 = .618; t2 = -0.58, p2 = .565), or Reflectiveness (t = -0.45, p = .656). These findings suggest that the LP-driven rubric pipeline can serve as an alternative solution.

Yun Wang, Zhaojun Ding, Xuansheng Wu et al.

Automated scoring plays a crucial role in education by reducing the reliance on human raters, offering scalable and immediate evaluation of student work. While large language models (LLMs) have shown strong potential in this task, their use as end-to-end raters faces challenges such as low accuracy, prompt sensitivity, limited interpretability, and rubric misalignment. These issues hinder the implementation of LLM-based automated scoring in assessment practice. To address the limitations, we propose AutoSCORE, a multi-agent LLM framework enhancing automated scoring via rubric-aligned Structured COmponent REcognition. With two agents, AutoSCORE first extracts rubric-relevant components from student responses and encodes them into a structured representation (i.e., Scoring Rubric Component Extraction Agent), which is then used to assign final scores (i.e., Scoring Agent). This design ensures that model reasoning follows a human-like grading process, enhancing interpretability and robustness. We evaluate AutoSCORE on four benchmark datasets from the ASAP benchmark, using both proprietary and open-source LLMs (GPT-4o, LLaMA-3.1-8B, and LLaMA-3.1-70B). Across diverse tasks and rubrics, AutoSCORE consistently improves scoring accuracy, human-machine agreement (QWK, correlations), and error metrics (MAE, RMSE) compared to single-agent baselines, with particularly strong benefits on complex, multi-dimensional rubrics, and especially large relative gains on smaller LLMs. These results demonstrate that structured component recognition combined with multi-agent design offers a scalable, reliable, and interpretable solution for automated scoring.

Ehsan Latif, Zirak Khan, Xiaoming Zhai

Scientific sketches (e.g., models) offer a powerful lens into students' conceptual understanding, yet AI-powered automated assessment of such free-form, visually diverse artifacts remains a critical challenge. Existing solutions often treat sketch evaluation as either an image classification task or monolithic vision-language models, which lack interpretability, pedagogical alignment, and adaptability across cognitive levels. To address these limitations, we present SketchMind, a cognitively grounded, multi-agent framework for evaluating and improving student-drawn scientific sketches. SketchMind comprises modular agents responsible for rubric parsing, sketch perception, cognitive alignment, and iterative feedback with sketch modification, enabling personalized and transparent evaluation. We evaluate SketchMind on a curated dataset of 3,575 student-generated sketches across six science assessment items with different highest order of Bloom's level that require students to draw models to explain phenomena. Compared to baseline GPT-4o performance without SRG (average accuracy: 55.6%), and with SRG integration achieves 77.1% average accuracy (+21.4% average absolute gain). We also demonstrate that multi-agent orchestration with SRG enhances SketchMind performance, for example, GPT-4.1 gains an average 8.9% increase in sketch prediction accuracy, outperforming single-agent pipelines across all items. Human evaluators rated the feedback and co-created sketches generated by \textsc{SketchMind} with GPT-4.1, which achieved an average of 4.1 out of 5, significantly higher than those of baseline models (e.g., 2.3 for GPT-4o). Experts noted the system's potential to meaningfully support conceptual growth through guided revision. Our code and (pending approval) dataset will be released to support reproducibility and future research in AI-driven education.

Arne Bewersdorff, Christian Hartmann, Marie Hornberger et al.

The integration of Artificial Intelligence (AI), particularly Large Language Model (LLM)-based systems, in education has shown promise in enhancing teaching and learning experiences. However, the advent of Multimodal Large Language Models (MLLMs) like GPT-4 with vision (GPT-4V), capable of processing multimodal data including text, sound, and visual inputs, opens a new era of enriched, personalized, and interactive learning landscapes in education. Grounded in theory of multimedia learning, this paper explores the transformative role of MLLMs in central aspects of science education by presenting exemplary innovative learning scenarios. Possible applications for MLLMs could range from content creation to tailored support for learning, fostering competencies in scientific practices, and providing assessment and feedback. These scenarios are not limited to text-based and uni-modal formats but can be multimodal, increasing thus personalization, accessibility, and potential learning effectiveness. Besides many opportunities, challenges such as data protection and ethical considerations become more salient, calling for robust frameworks to ensure responsible integration. This paper underscores the necessity for a balanced approach in implementing MLLMs, where the technology complements rather than supplants the educator's role, ensuring thus an effective and ethical use of AI in science education. It calls for further research to explore the nuanced implications of MLLMs on the evolving role of educators and to extend the discourse beyond science education to other disciplines. Through the exploration of potentials, challenges, and future implications, we aim to contribute to a preliminary understanding of the transformative trajectory of MLLMs in science education and beyond.

Xiaoming Zhai, Matthew Nyaaba, Wenchao Ma

This study aimed to examine an assumption that generative artificial intelligence (GAI) tools can overcome the cognitive intensity that humans suffer when solving problems. We compared the performance of ChatGPT and GPT-4 on 2019 NAEP science assessments with students by cognitive demands of the items. Fifty-four tasks were coded by experts using a two-dimensional cognitive load framework, including task cognitive complexity and dimensionality. ChatGPT and GPT-4 responses were scored using the scoring keys of NAEP. The analysis of the available data was based on the average student ability scores for students who answered each item correctly and the percentage of students who responded to individual items. Results showed that both ChatGPT and GPT-4 consistently outperformed most students who answered the NAEP science assessments. As the cognitive demand for NAEP tasks increases, statistically higher average student ability scores are required to correctly address the questions. This pattern was observed for students in grades 4, 8, and 12, respectively. However, ChatGPT and GPT-4 were not statistically sensitive to the increase in cognitive demands of the tasks, except for Grade 4. As the first study focusing on comparing GAI and K-12 students in problem-solving in science, this finding implies the need for changes to educational objectives to prepare students with competence to work with GAI tools in the future. Education ought to emphasize the cultivation of advanced cognitive skills rather than depending solely on tasks that demand cognitive intensity. This approach would foster critical thinking, analytical skills, and the application of knowledge in novel contexts. Findings also suggest the need for innovative assessment practices by moving away from cognitive intensity tasks toward creativity and analytical skills to avoid the negative effects of GAI on testing more efficiently.

Gyeong-Geon Lee, Ehsan Latif, Lehong Shi et al.

This study compared the classification performance of Gemini Pro and GPT-4V in educational settings. Employing visual question answering (VQA) techniques, the study examined both models' abilities to read text-based rubrics and then automatically score student-drawn models in science education. We employed both quantitative and qualitative analyses using a dataset derived from student-drawn scientific models and employing NERIF (Notation-Enhanced Rubrics for Image Feedback) prompting methods. The findings reveal that GPT-4V significantly outperforms Gemini Pro in terms of scoring accuracy and Quadratic Weighted Kappa. The qualitative analysis reveals that the differences may be due to the models' ability to process fine-grained texts in images and overall image classification performance. Even adapting the NERIF approach by further de-sizing the input images, Gemini Pro seems not able to perform as well as GPT-4V. The findings suggest GPT-4V's superior capability in handling complex multimodal educational tasks. The study concludes that while both models represent advancements in AI, GPT-4V's higher performance makes it a more suitable tool for educational applications involving multimodal data interpretation.

Yiwei Li, Huaqin Zhao, Hanqi Jiang et al.

The rapid advances in Large Language Models (LLMs) have the potential to transform manufacturing industry, offering new opportunities to optimize processes, improve efficiency, and drive innovation. This paper provides a comprehensive exploration of the integration of LLMs into the manufacturing domain, focusing on their potential to automate and enhance various aspects of manufacturing, from product design and development to quality control, supply chain optimization, and talent management. Through extensive evaluations across multiple manufacturing tasks, we demonstrate the remarkable capabilities of state-of-the-art LLMs, such as GPT-4V, in understanding and executing complex instructions, extracting valuable insights from vast amounts of data, and facilitating knowledge sharing. We also delve into the transformative potential of LLMs in reshaping manufacturing education, automating coding processes, enhancing robot control systems, and enabling the creation of immersive, data-rich virtual environments through the industrial metaverse. By highlighting the practical applications and emerging use cases of LLMs in manufacturing, this paper aims to provide a valuable resource for professionals, researchers, and decision-makers seeking to harness the power of these technologies to address real-world challenges, drive operational excellence, and unlock sustainable growth in an increasingly competitive landscape.

Ehsan Latif, Yifan Zhou, Shuchen Guo et al.

As artificial intelligence (AI) continues to advance, it demonstrates capabilities comparable to human intelligence, with significant potential to transform education and workforce development. This study evaluates OpenAI o1-preview's ability to perform higher-order cognitive tasks across 14 dimensions, including critical thinking, systems thinking, computational thinking, design thinking, metacognition, data literacy, creative thinking, abstract reasoning, quantitative reasoning, logical reasoning, analogical reasoning, and scientific reasoning. We used validated instruments like the Ennis-Weir Critical Thinking Essay Test and the Biological Systems Thinking Test to compare the o1-preview's performance with human performance systematically. Our findings reveal that o1-preview outperforms humans in most categories, achieving 150% better results in systems thinking, computational thinking, data literacy, creative thinking, scientific reasoning, and abstract reasoning. However, compared to humans, it underperforms by around 25% in logical reasoning, critical thinking, and quantitative reasoning. In analogical reasoning, both o1-preview and humans achieved perfect scores. Despite these strengths, the o1-preview shows limitations in abstract reasoning, where human psychology students outperform it, highlighting the continued importance of human oversight in tasks requiring high-level abstraction. These results have significant educational implications, suggesting a shift toward developing human skills that complement AI, such as creativity, abstract reasoning, and critical thinking. This study emphasizes the transformative potential of AI in education and calls for a recalibration of educational goals, teaching methods, and curricula to align with an AI-driven world.

Shuchen Guo, Ehsan Latif, Yifan Zhou et al.

This study investigates the use of generative AI and multi-agent systems to provide automatic feedback in educational contexts, particularly for student constructed responses in science assessments. The research addresses a key gap in the field by exploring how multi-agent systems, called AutoFeedback, can improve the quality of GenAI-generated feedback, overcoming known issues such as over-praise and over-inference that are common in single-agent large language models (LLMs). The study developed a multi-agent system consisting of two AI agents: one for generating feedback and another for validating and refining it. The system was tested on a dataset of 240 student responses, and its performance was compared to that of a single-agent LLM. Results showed that AutoFeedback significantly reduced the occurrence of over-praise and over-inference errors, providing more accurate and pedagogically sound feedback. The findings suggest that multi-agent systems can offer a more reliable solution for generating automated feedback in educational settings, highlighting their potential for scalable and personalized learning support. These results have important implications for educators and researchers seeking to leverage AI in formative assessments, offering a pathway to more effective feedback mechanisms that enhance student learning outcomes.

Gyeong-Geon Lee, Xiaoming Zhai

Educational scholars have analyzed various image data acquired from teaching and learning situations, such as photos that shows classroom dynamics, students' drawings with regard to the learning content, textbook illustrations, etc. Unquestioningly, most qualitative analysis of and explanation on image data have been conducted by human researchers, without machine-based automation. It was partially because most image processing artificial intelligence models were not accessible to general educational scholars or explainable due to their complex deep neural network architecture. However, the recent development of Visual Question Answering (VQA) techniques is accomplishing usable visual language models, which receive from the user a question about the given image and returns an answer, both in natural language. Particularly, GPT-4V released by OpenAI, has wide opened the state-of-the-art visual langauge model service so that VQA could be used for a variety of purposes. However, VQA and GPT-4V have not yet been applied to educational studies much. In this position paper, we suggest that GPT-4V contributes to realizing VQA for education. By 'realizing' VQA, we denote two meanings: (1) GPT-4V realizes the utilization of VQA techniques by any educational scholars without technical/accessibility barrier, and (2) GPT-4V makes educational scholars realize the usefulness of VQA to educational research. Given these, this paper aims to introduce VQA for educational studies so that it provides a milestone for educational research methodology. In this paper, chapter II reviews the development of VQA techniques, which primes with the release of GPT-4V. Chapter III reviews the use of image analysis in educational studies. Chapter IV demonstrates how GPT-4V can be used for each research usage reviewed in Chapter III, with operating prompts provided. Finally, chapter V discusses the future implications.

Gyeong-Geon Lee, Seonyeong Mun, Myeong-Kyeong Shin et al.

This research aims to demonstrate that AI can function not only as a tool for learning, but also as an intelligent agent with which humans can engage in collaborative learning (CL) to change epistemic practices in science classrooms. We adopted a design and development research approach, following the Analysis, Design, Development, Implementation and Evaluation (ADDIE) model, to prototype a tangible instructional system called Collaborative Learning with AI Speakers (CLAIS). The CLAIS system is designed to have 3-4 human learners join an AI speaker to form a small group, where humans and AI are considered as peers participating in the Jigsaw learning process. The development was carried out using the NUGU AI speaker platform. The CLAIS system was successfully implemented in a Science Education course session with 15 pre-service elementary science teachers. The participants evaluated the CLAIS system through mixed methods surveys as teachers, learners, peers, and users. Quantitative data showed that the participants' Intelligent-Technological, Pedagogical, And Content Knowledge was significantly increased after the CLAIS session, the perception of the CLAIS learning experience was positive, the peer assessment on AI speakers and human peers was different, and the user experience was ambivalent. Qualitative data showed that the participants anticipated future changes in the epistemic process in science classrooms, while acknowledging technical issues such as speech recognition performance and response latency. This study highlights the potential of Human-AI Collaboration for knowledge co-construction in authentic classroom settings and exemplify how AI could shape the future landscape of epistemic practices in the classroom.

Peng Shu, Junhao Chen, Zhengliang Liu et al.

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of tasks and domains. However, their performance in low-resource language translation, particularly when translating into these languages, remains underexplored. This gap poses significant challenges, as linguistic barriers hinder the cultural preservation and development of minority communities. To address this issue, this paper introduces a novel retrieval-based method that enhances translation quality for low-resource languages by focusing on key terms, which involves translating keywords and retrieving corresponding examples from existing data. To evaluate the effectiveness of this method, we conducted experiments translating from English into three low-resource languages: Cherokee, a critically endangered indigenous language of North America; Tibetan, a historically and culturally significant language in Asia; and Manchu, a language with few remaining speakers. Our comparison with the zero-shot performance of GPT-4o and LLaMA 3.1 405B, highlights the significant challenges these models face when translating into low-resource languages. In contrast, our retrieval-based method shows promise in improving both word-level accuracy and overall semantic understanding by leveraging existing resources more effectively.

Luyang Fang, Xiaowei Yu, Jiazhang Cai et al.

The exponential growth of Large Language Models (LLMs) continues to highlight the need for efficient strategies to meet ever-expanding computational and data demands. This survey provides a comprehensive analysis of two complementary paradigms: Knowledge Distillation (KD) and Dataset Distillation (DD), both aimed at compressing LLMs while preserving their advanced reasoning capabilities and linguistic diversity. We first examine key methodologies in KD, such as task-specific alignment, rationale-based training, and multi-teacher frameworks, alongside DD techniques that synthesize compact, high-impact datasets through optimization-based gradient matching, latent space regularization, and generative synthesis. Building on these foundations, we explore how integrating KD and DD can produce more effective and scalable compression strategies. Together, these approaches address persistent challenges in model scalability, architectural heterogeneity, and the preservation of emergent LLM abilities. We further highlight applications across domains such as healthcare and education, where distillation enables efficient deployment without sacrificing performance. Despite substantial progress, open challenges remain in preserving emergent reasoning and linguistic diversity, enabling efficient adaptation to continually evolving teacher models and datasets, and establishing comprehensive evaluation protocols. By synthesizing methodological innovations, theoretical foundations, and practical insights, our survey charts a path toward sustainable, resource-efficient LLMs through the tighter integration of KD and DD principles.

Shaochen Xu, Yifan Zhou, Zhengliang Liu et al.

Artificial Intelligence (AI) has become essential in modern healthcare, with large language models (LLMs) offering promising advances in clinical decision-making. Traditional model-based approaches, including those leveraging in-context demonstrations and those with specialized medical fine-tuning, have demonstrated strong performance in medical language processing but struggle with real-time adaptability, multi-step reasoning, and handling complex medical tasks. Agent-based AI systems address these limitations by incorporating reasoning traces, tool selection based on context, knowledge retrieval, and both short- and long-term memory. These additional features enable the medical AI agent to handle complex medical scenarios where decision-making should be built on real-time interaction with the environment. Therefore, unlike conventional model-based approaches that treat medical queries as isolated questions, medical AI agents approach them as complex tasks and behave more like human doctors. In this paper, we study the choice of the backbone LLM for medical AI agents, which is the foundation for the agent's overall reasoning and action generation. In particular, we consider the emergent o1 model and examine its impact on agents' reasoning, tool-use adaptability, and real-time information retrieval across diverse clinical scenarios, including high-stakes settings such as intensive care units (ICUs). Our findings demonstrate o1's ability to enhance diagnostic accuracy and consistency, paving the way for smarter, more responsive AI tools that support better patient outcomes and decision-making efficacy in clinical practice.

Jennifer Kleiman, Yizhu Gao, Xin Xia et al.

Argumentation is a core practice in STEM education, but its productivity depends on who participates and how they interact. Higher-achieving students often dominate the talk and decision-making, while lower-achieving peers may disengage, defer, or comply without contributing substantive reasoning. Forming groups strategically based on students' stances and argumentation skills could help foster inclusive, evidence-based discourse. In practice, however, teachers are constrained in implementing this grouping strategy because it requires real-time insight into students' positions and the quality of their argumentation, information that is difficult to assess reliably and at scale during instruction. We present a generative AI-powered system, ArguAgent, that creates groups optimizing for stance heterogeneity while constraining argumentation quality differences to +/-1 level on a validated learning progression. ArguAgent uses a two-component assessment pipeline: first scoring student arguments on a 0-4 rubric, then clustering positions via semantic analysis. We validated the scoring component against human expert consensus (Krippendorff's ααα = 0.817) using 200 expert-generated scores. Testing three OpenAI models (GPT-4o-mini, GPT-5.1, GPT-5.2) with identical calibrated prompts, we found that systematic prompt engineering informed by human disagreement analysis contributed 89% of scoring improvement (QWK: 0.531 to 0.686), while model upgrades contributed an additional 11% (QWK: 0.686 to 0.708). Simulation testing across 100 classes demonstrated that the grouping algorithm achieves 95.4% of groups that meet both design criteria, a 3.2x improvement over random assignment. These results suggest ArguAgent can enable real-time, theoretically grounded grouping that promotes productive STEM argumentation in classrooms.

Ehsan Latif, Gyeong-Geon Lee, Knut Neumann et al.

The advancement of natural language processing has paved the way for automated scoring systems in various languages, such as German (e.g., German BERT [G-BERT]). Automatically scoring written responses to science questions in German is a complex task and challenging for standard G-BERT as they lack contextual knowledge in the science domain and may be unaligned with student writing styles. This paper presents a contextualized German Science Education BERT (G-SciEdBERT), an innovative large language model tailored for scoring German-written responses to science tasks and beyond. Using G-BERT, we pre-trained G-SciEdBERT on a corpus of 30K German written science responses with 3M tokens on the Programme for International Student Assessment (PISA) 2018. We fine-tuned G-SciEdBERT on an additional 20K student-written responses with 2M tokens and examined the scoring accuracy. We then compared its scoring performance with G-BERT. Our findings revealed a substantial improvement in scoring accuracy with G-SciEdBERT, demonstrating a 10.2% increase of quadratic weighted Kappa compared to G-BERT (mean difference = 0.1026, SD = 0.069). These insights underline the significance of specialized language models like G-SciEdBERT, which is trained to enhance the accuracy of contextualized automated scoring, offering a substantial contribution to the field of AI in education.

Ehsan Latif, Luyang Fang, Ping Ma et al.

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on resource-constrained devices. Our methodology involves training the smaller student model (Neural Network) using the prediction probabilities (as soft labels) of the LLM, which serves as a teacher model. This is achieved through a specialized loss function tailored to learn from the LLM's output probabilities, ensuring that the student model closely mimics the teacher's performance. To validate the performance of the KD approach, we utilized a large dataset, 7T, containing 6,684 student-written responses to science questions and three mathematical reasoning datasets with student-written responses graded by human experts. We compared accuracy with state-of-the-art (SOTA) distilled models, TinyBERT, and artificial neural network (ANN) models. Results have shown that the KD approach has 3% and 2% higher scoring accuracy than ANN and TinyBERT, respectively, and comparable accuracy to the teacher model. Furthermore, the student model size is 0.03M, 4,000 times smaller in parameters and x10 faster in inferencing than the teacher model and TinyBERT, respectively. The significance of this research lies in its potential to make advanced AI technologies accessible in typical educational settings, particularly for automatic scoring.

Jie Yang, Ehsan Latif, Yuze He et al.

The development of explanations for scientific phenomena is essential in science assessment, but scoring student-written explanations remains challenging and resource-intensive. Large language models (LLMs) have shown promise in addressing this issue, particularly in alphabetic languages like English. However, their applicability to logographic languages is less explored. This study investigates the potential of fine-tuning ChatGPT, a leading LLM, to automatically score scientific explanations written in Chinese. Student responses to seven scientific explanation tasks were collected and automatically scored, with scoring accuracy examined in relation to reasoning complexity using the Kendall correlation. A qualitative analysis explored how linguistic features influenced scoring accuracy. The results show that domain-specific adaptation enables ChatGPT to score Chinese scientific explanations with accuracy. However, scoring accuracy correlates with reasoning complexity: a negative correlation for lower-level responses and a positive one for higher-level responses. The model overrates complex reasoning in low-level responses with intricate sentence structures and underrates high-level responses using concise causal reasoning. These correlations stem from linguistic features--simplicity and clarity enhance accuracy for lower-level responses, while comprehensiveness improves accuracy for higher-level ones. Simpler, shorter responses tend to score more accurately at lower levels, whereas longer, information-rich responses yield better accuracy at higher levels. These findings demonstrate the effectiveness of LLMs in automatic scoring within a Chinese context and emphasize the importance of linguistic features and reasoning complexity in fine-tuning scoring models for educational assessments.

Xiaoming Zhai

This chapter focuses on the transformative role of Artificial Intelligence (AI) and Machine Learning (ML) in science assessments. The paper begins with a discussion of the Framework for K-12 Science Education, which calls for a shift from conceptual learning to knowledge-in-use. This shift necessitates the development of new types of assessments that align with the Framework's three dimensions: science and engineering practices, disciplinary core ideas, and crosscutting concepts. The paper further highlights the limitations of traditional assessment methods like multiple-choice questions, which often fail to capture the complexities of scientific thinking and three-dimensional learning in science. It emphasizes the need for performance-based assessments that require students to engage in scientific practices like modeling, explanation, and argumentation. The paper achieves three major goals: reviewing the current state of ML-based assessments in science education, introducing a framework for scoring accuracy in ML-based automatic assessments, and discussing future directions and challenges. It delves into the evolution of ML-based automatic scoring systems, discussing various types of ML, like supervised, unsupervised, and semi-supervised learning. These systems can provide timely and objective feedback, thus alleviating the burden on teachers. The paper concludes by exploring pre-trained models like BERT and finetuned ChatGPT, which have shown promise in assessing students' written responses effectively.

Ehsan Latif, Yifan Zhou, Shuchen Guo et al.

This study evaluates the performance of OpenAI's o1-preview model in higher-order cognitive domains, including critical thinking, systematic thinking, computational thinking, data literacy, creative thinking, logical reasoning, and scientific reasoning. Using established benchmarks, we compared the o1-preview models's performance to human participants from diverse educational levels. o1-preview achieved a mean score of 24.33 on the Ennis-Weir Critical Thinking Essay Test (EWCTET), surpassing undergraduate (13.8) and postgraduate (18.39) participants (z = 1.60 and 0.90, respectively). In systematic thinking, it scored 46.1, SD = 4.12 on the Lake Urmia Vignette, significantly outperforming the human mean (20.08, SD = 8.13, z = 3.20). For data literacy, o1-preview scored 8.60, SD = 0.70 on Merk et al.'s "Use Data" dimension, compared to the human post-test mean of 4.17, SD = 2.02 (z = 2.19). On creative thinking tasks, the model achieved originality scores of 2.98, SD = 0.73, higher than the human mean of 1.74 (z = 0.71). In logical reasoning (LogiQA), it outperformed humans with average 90%, SD = 10% accuracy versus 86%, SD = 6.5% (z = 0.62). For scientific reasoning, it achieved near-perfect performance (mean = 0.99, SD = 0.12) on the TOSLS,, exceeding the highest human scores of 0.85, SD = 0.13 (z = 1.78). While o1-preview excelled in structured tasks, it showed limitations in problem-solving and adaptive reasoning. These results demonstrate the potential of AI to complement education in structured assessments but highlight the need for ethical oversight and refinement for broader applications.

Shuchen Guo, Yun Wang, Jichao Yu et al.

This study investigated potential scoring biases and disparities toward English Language Learners (ELLs) when using automatic scoring systems for middle school students' written responses to science assessments. We specifically focus on examining how unbalanced training data with ELLs contributes to scoring bias and disparities. We fine-tuned BERT with four datasets: responses from (1) ELLs, (2) non-ELLs, (3) a mixed dataset reflecting the real-world proportion of ELLs and non-ELLs (unbalanced), and (4) a balanced mixed dataset with equal representation of both groups. The study analyzed 21 assessment items: 10 items with about 30,000 ELL responses, five items with about 1,000 ELL responses, and six items with about 200 ELL responses. Scoring accuracy (Acc) was calculated and compared to identify bias using Friedman tests. We measured the Mean Score Gaps (MSGs) between ELLs and non-ELLs and then calculated the differences in MSGs generated through both the human and AI models to identify the scoring disparities. We found that no AI bias and distorted disparities between ELLs and non-ELLs were found when the training dataset was large enough (ELL = 30,000 and ELL = 1,000), but concerns could exist if the sample size is limited (ELL = 200).

Ehsan Latif, Xiaoming Zhai

Data privacy remains a critical concern in educational research, requiring strict adherence to ethical standards and regulatory protocols. While traditional approaches rely on anonymization and centralized data collection, they often expose raw student data to security vulnerabilities and impose substantial logistical overhead. In this study, we propose a federated learning (FL) framework for automated scoring of educational assessments that eliminates the need to share sensitive data across institutions. Our approach leverages parameter-efficient fine-tuning of large language models (LLMs) with Low-Rank Adaptation (LoRA), enabling each client (school) to train locally while sharing only optimized model updates. To address data heterogeneity, we implement an adaptive weighted aggregation strategy that considers both client performance and data volume. We benchmark our model against two state-of-the-art FL methods and a centralized learning baseline using NGSS-aligned multi-label science assessment data from nine middle schools. Results show that our model achieves the highest accuracy (94.5%) among FL approaches, and performs within 0.5-1.0 percentage points of the centralized model on these metrics. Additionally, it achieves comparable rubric-level scoring accuracy, with only a 1.3% difference in rubric match and a lower score deviation (MAE), highlighting its effectiveness in preserving both prediction quality and interpretability.

Newnew Deng, Edward Jiusi Liu, Xiaoming Zhai

The use of generative AI (GAI) among university students is rapidly increasing, yet empirical research on students' GAI use and the factors influencing it remains limited. To address this gap, we surveyed 363 undergraduate and graduate students in the United States, examining their GAI usage and how it relates to demographic variables and personality traits based on the Big Five model (i.e., extraversion, agreeableness, conscientiousness, and emotional stability, and intellect/imagination). Our findings reveal: (a) Students in higher academic years are more inclined to use GAI and prefer it over traditional resources. (b) Non-native English speakers use and adopt GAI more readily than native speakers. (c) Compared to White, Asian students report higher GAI usage, perceive greater academic benefits, and express a stronger preference for it. Similarly, Black students report a more positive impact of GAI on their academic performance. Personality traits also play a significant role in shaping perceptions and usage of GAI. After controlling demographic factors, we found that personality still significantly predicts GAI use and attitudes: (a) Students with higher conscientiousness use GAI less. (b) Students who are higher in agreeableness perceive a less positive impact of GAI on academic performance and express more ethical concerns about using it for academic work. (c) Students with higher emotional stability report a more positive impact of GAI on learning and fewer concerns about its academic use. (d) Students with higher extraversion show a stronger preference for GAI over traditional resources. (e) Students with higher intellect/imagination tend to prefer traditional resources. These insights highlight the need for universities to provide personalized guidance to ensure students use GAI effectively, ethically, and equitably in their academic pursuits.

Arne Bewersdorff, Nejla Yuruk, Xiaoming Zhai

In science education, students frequently construct hand-drawn visual models of scientific phenomena. These drawings rely on a visual structure where information is encoded through visual objects, their attributes, and relationships. Multimodal large language models (MLLMs) are increasingly used to generate feedback on students' hand-drawn scientific models. However, the validity of such feedback depends on whether model claims are grounded in the specific visual evidence of the student drawing. This study uncovers grounding failures, consistent with modal decoupling, in off-the-shelf MLLM feedback, where outputs remain pedagogically plausible in form while contradicting the drawing or treating depicted elements as missing. Using N = 150 middle school drawings from a kinetic molecular theory unit spanning five modeling tasks and three competence levels, we generated N = 300 feedback instances with GPT-5.1. All outputs were coded for four grounding error types: object mismatch, attribute mismatch, relation mismatch, and false absence. Grounding failures were common: 41.3% of feedback instances contained at least one error. An inventory-list-first workflow reduced several error categories and lowered the overall error rate, but it did not resolve the underlying limitation: approximately one in three outputs remained flawed, with false absence as the dominant failure mode. Moreover, feedback that appears visually grounded offered little diagnostic value for identifying invalid instances. The findings indicate that modal decoupling is a substantial limitation and that valid feedback will require grounding mechanisms beyond common prompting strategies.

Luyang Fang, Ehsan Latif, Haoran Lu et al.

Automatic scoring of student responses enhances efficiency in education, but deploying a separate neural network for each task increases storage demands, maintenance efforts, and redundant computations. To address these challenges, this paper introduces the Gromov-Wasserstein Scoring Model Merging (GW-SMM) method, which merges models based on feature distribution similarities measured via the Gromov-Wasserstein distance. Our approach begins by extracting features from student responses using individual models, capturing both item-specific context and unique learned representations. The Gromov-Wasserstein distance then quantifies the similarity between these feature distributions, identifying the most compatible models for merging. Models exhibiting the smallest pairwise distances, typically in pairs or trios, are merged by combining only the shared layers preceding the classification head. This strategy results in a unified feature extractor while preserving separate classification heads for item-specific scoring. We validated our approach against human expert knowledge and a GPT-o1-based merging method. GW-SMM consistently outperformed both, achieving a higher micro F1 score, macro F1 score, exact match accuracy, and per-label accuracy. The improvements in micro F1 and per-label accuracy were statistically significant compared to GPT-o1-based merging (p=0.04, p=0.01). Additionally, GW-SMM reduced storage requirements by half without compromising much accuracy, demonstrating its computational efficiency alongside reliable scoring performance.

Ehsan Latif, Xiaoming Zhai

The integration of Artificial Intelligence (AI) in education requires scalable and efficient frameworks that balance performance, adaptability, and cost. This paper addresses these needs by proposing a shared backbone model architecture enhanced with lightweight LoRA adapters for task-specific fine-tuning, targeting the automated scoring of student responses across 27 mutually exclusive tasks. By achieving competitive performance (average QWK of 0.848 compared to 0.888 for fully fine-tuned models) while reducing GPU memory consumption by 60% and inference latency by 40%, the framework demonstrates significant efficiency gains. This approach aligns with the workshop's focus on improving language models for educational tasks, creating responsible innovations for cost-sensitive deployment, and supporting educators by streamlining assessment workflows. The findings underscore the potential of scalable AI to enhance learning outcomes while maintaining fairness and transparency in automated scoring systems.

Zhaojun Ding, Zhengliang Liu, Hanqi Jiang et al.

Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource languages due to limited training data and difficulty in understanding cultural nuances. Research is now focusing on multilingual models to improve LLM performance for these languages. Education in these languages also struggles with a lack of resources and qualified teachers, particularly in underdeveloped regions. Here, LLMs can be transformative, supporting innovative methods like community-driven learning and digital platforms. This paper discusses how LLMs could enhance education for low-resource languages, emphasizing practical applications and benefits.

Xiaoming Zhai, Kent Crippen

This introductory chapter explores the transformative role of artificial intelligence (AI) in reshaping the landscape of science education. Positioned at the intersection of tradition and innovation, AI is altering educational goals, procedures, learning materials, assessment practices, and desired outcomes. We highlight how AI-supported tools, such as intelligent tutoring systems, adaptive learning platforms, automated feedback, and generative content creation--enhance personalization, efficiency, and equity while fostering competencies essential for an AI-driven society, including critical thinking, creativity, and interdisciplinary collaboration. At the same time, this chapter examines the ethical, social, and pedagogical challenges that arise, particularly issues of fairness, transparency, accountability, privacy, and human oversight. To address these tensions, we argue that a Responsible and Ethical Principles (REP) framework is needed to offer guidance for aligning AI integration with values of fairness, scientific integrity, and democratic participation. Through this lens, we synthesize the changes brought to each of the five transformative aspects and the approaches introduced to meet the changes according to the REP framework. We argue that AI should be viewed not as a replacement for human teachers and learners but as a partner that supports inquiry, enriches assessment, and expands access to authentic scientific practices. Aside from what is changing, we conclude by exploring the roles that remain uniquely human, engaging as moral and relational anchors in classrooms, bringing interpretive and ethical judgement, fostering creativity, imagination, and curiosity, and co-constructing meaning through dialogue and community, and assert that these qualities must remain central if AI is to advance equity, integrity, and human flourishing in science education.

Hanzhi Yan, Qin Lu, Xianqiao Wang et al.

While large language models (LLMs) have demonstrated remarkable versatility across a wide range of general tasks, their effectiveness often diminishes in domain-specific applications due to inherent knowledge gaps. Moreover, their performance typically declines when addressing complex problems that require multi-step reasoning and analysis. In response to these challenges, we propose leveraging both LLMs and AI agents to develop education assistants aimed at enhancing undergraduate learning in biomechanics courses that focus on analyzing the force and moment in the musculoskeletal system of the human body. To achieve our goal, we construct a dual-module framework to enhance LLM performance in biomechanics educational tasks: 1) we apply Retrieval-Augmented Generation (RAG) to improve the specificity and logical consistency of LLM's responses to the conceptual true/false questions; 2) we build a Multi-Agent System (MAS) to solve calculation-oriented problems involving multi-step reasoning and code execution. Specifically, we evaluate the performance of several LLMs, i.e., Qwen-1.0-32B, Qwen-2.5-32B, and Llama-70B, on a biomechanics dataset comprising 100 true/false conceptual questions and problems requiring equation derivation and calculation. Our results demonstrate that RAG significantly enhances the performance and stability of LLMs in answering conceptual questions, surpassing those of vanilla models. On the other hand, the MAS constructed using multiple LLMs demonstrates its ability to perform multi-step reasoning, derive equations, execute code, and generate explainable solutions for tasks that require calculation. These findings demonstrate the potential of applying RAG and MAS to enhance LLM performance for specialized courses in engineering curricula, providing a promising direction for developing intelligent tutoring in engineering education.

Matthew Nyaaba, Macharious Nabang, Patrick Kyeremeh et al.

STEAM education in many parts of the Global South remains abstract and weakly connected to learners sociocultural realities. This study examines how human experts evaluate the capacity of Generative AI (GenAI) to contextualize STEAM instruction in these settings. Using a convergent mixed-methods design grounded in human-centered and culturally responsive pedagogy, four STEAM education experts reviewed standardized Ghana NaCCA lesson plans and GenAI-generated lessons created with a customized Culturally Responsive Lesson Planner (CRLP). Quantitative data were collected with a validated 25-item Culturally Responsive Pedagogy Rubric assessing bias awareness, cultural representation, contextual relevance, linguistic responsiveness, and teacher agency. Qualitative reflections provided additional insight into the pedagogical and cultural dynamics of each lesson. Findings show that GenAI, especially through the CRLP, improved connections between abstract standards and learners lived experiences. Teacher Agency was the strongest domain, while Cultural Representation was the weakest. CRLP-generated lessons were rated as more culturally grounded and pedagogically engaging. However, GenAI struggled to represent Ghana's cultural diversity, often producing surface-level references, especially in Mathematics and Computing. Experts stressed the need for teacher mediation, community input, and culturally informed refinement of AI outputs. Future work should involve classroom trials, broader expert participation, and fine-tuning with Indigenous corpora.