Shijin Wang

Beichen Zhang, Kun Zhou, Xilin Wei et al.

Chain-of-thought prompting~(CoT) and tool augmentation have been validated in recent work as effective practices for improving large language models~(LLMs) to perform step-by-step reasoning on complex math-related tasks. However, most existing math reasoning datasets may be not able to fully evaluate and analyze the ability of LLMs in manipulating tools and performing reasoning, as they may only require very few invocations of tools or miss annotations for evaluating intermediate reasoning steps. To address the issue, we construct \textbf{CARP}, a new Chinese dataset consisting of 4,886 computation-intensive algebra problems with formulated annotations on intermediate steps. In CARP, we test four LLMs with CoT prompting, and find that they are all prone to make mistakes at the early steps of the solution, leading to wrong answers. Based on this finding, we propose a new approach that can deliberate the reasoning steps with tool interfaces, namely \textbf{DELI}. In DELI, we first initialize a step-by-step solution based on retrieved exemplars, then iterate two deliberation procedures that check and refine the intermediate steps of the generated solution, from the perspectives of tool manipulation and natural language reasoning, until obtaining converged solutions or reaching the maximum turn. Experimental results on CARP and six other datasets show that the proposed DELI mostly outperforms competitive baselines, and can further boost the performance of existing CoT methods. Our data and code are available in \url{https://github.com/RUCAIBox/CARP}.

Yiming Cui, Wanxiang Che, Shijin Wang et al.

Pre-trained Language Model (PLM) has become a representative foundation model in the natural language processing field. Most PLMs are trained with linguistic-agnostic pre-training tasks on the surface form of the text, such as the masked language model (MLM). To further empower the PLMs with richer linguistic features, in this paper, we aim to propose a simple but effective way to learn linguistic features for pre-trained language models. We propose LERT, a pre-trained language model that is trained on three types of linguistic features along with the original MLM pre-training task, using a linguistically-informed pre-training (LIP) strategy. We carried out extensive experiments on ten Chinese NLU tasks, and the experimental results show that LERT could bring significant improvements over various comparable baselines. Furthermore, we also conduct analytical experiments in various linguistic aspects, and the results prove that the design of LERT is valid and effective. Resources are available at https://github.com/ymcui/LERT

Yuqing Huang, Rongyang Zhang, Xuesong He et al.

There is a growing interest in the role that LLMs play in chemistry which lead to an increased focus on the development of LLMs benchmarks tailored to chemical domains to assess the performance of LLMs across a spectrum of chemical tasks varying in type and complexity. However, existing benchmarks in this domain fail to adequately meet the specific requirements of chemical research professionals. To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks. Specifically, ChemEval identified 4 crucial progressive levels in chemistry, assessing 12 dimensions of LLMs across 42 distinct chemical tasks which are informed by open-source data and the data meticulously crafted by chemical experts, ensuring that the tasks have practical value and can effectively evaluate the capabilities of LLMs. In the experiment, we evaluate 12 mainstream LLMs on ChemEval under zero-shot and few-shot learning contexts, which included carefully selected demonstration examples and carefully designed prompts. The results show that while general LLMs like GPT-4 and Claude-3.5 excel in literature understanding and instruction following, they fall short in tasks demanding advanced chemical knowledge. Conversely, specialized LLMs exhibit enhanced chemical competencies, albeit with reduced literary comprehension. This suggests that LLMs have significant potential for enhancement when tackling sophisticated tasks in the field of chemistry. We believe our work will facilitate the exploration of their potential to drive progress in chemistry. Our benchmark and analysis will be available at {\color{blue} \url{https://github.com/USTC-StarTeam/ChemEval}}.

Yan Zhuang, Qi Liu, Zachary A. Pardos et al.

As AI systems continue to evolve, their rigorous evaluation becomes crucial for their development and deployment. Researchers have constructed various large-scale benchmarks to determine their capabilities, typically against a gold-standard test set and report metrics averaged across all items. However, this static evaluation paradigm increasingly shows its limitations, including high evaluation costs, data contamination, and the impact of low-quality or erroneous items on evaluation reliability and efficiency. In this Position, drawing from human psychometrics, we discuss a paradigm shift from static evaluation methods to adaptive testing. This involves estimating the characteristics or value of each test item in the benchmark, and tailoring each model's evaluation instead of relying on a fixed test set. This paradigm provides robust ability estimation, uncovering the latent traits underlying a model's observed scores. This position paper analyze the current possibilities, prospects, and reasons for adopting psychometrics in AI evaluation. We argue that psychometrics, a theory originating in the 20th century for human assessment, could be a powerful solution to the challenges in today's AI evaluations.

Wayne Xin Zhao, Kun Zhou, Beichen Zhang et al.

Although pre-trained language models~(PLMs) have recently advanced the research progress in mathematical reasoning, they are not specially designed as a capable multi-task solver, suffering from high cost for multi-task deployment (\eg a model copy for a task) and inferior performance on complex mathematical problems in practical applications. To address these issues, in this paper, we propose \textbf{JiuZhang~2.0}, a unified Chinese PLM specially for multi-task mathematical problem solving. Our idea is to maintain a moderate-sized model and employ the \emph{cross-task knowledge sharing} to improve the model capacity in a multi-task setting. Specially, we construct a Mixture-of-Experts~(MoE) architecture for modeling mathematical text, so as to capture the common mathematical knowledge across tasks. For optimizing the MoE architecture, we design \emph{multi-task continual pre-training} and \emph{multi-task fine-tuning} strategies for multi-task adaptation. These training strategies can effectively decompose the knowledge from the task data and establish the cross-task sharing via expert networks. In order to further improve the general capacity of solving different complex tasks, we leverage large language models~(LLMs) as complementary models to iteratively refine the generated solution by our PLM, via in-context learning. Extensive experiments have demonstrated the effectiveness of our model.

Fei Wang, Weibo Gao, Qi Liu et al.

Cognitive diagnosis has been developed for decades as an effective measurement tool to evaluate human cognitive status such as ability level and knowledge mastery. It has been applied to a wide range of fields including education, sport, psychological diagnosis, etc. By providing better awareness of cognitive status, it can serve as the basis for personalized services such as well-designed medical treatment, teaching strategy and vocational training. This paper aims to provide a survey of current models for cognitive diagnosis, with more attention on new developments using machine learning-based methods. By comparing the model structures, parameter estimation algorithms, model evaluation methods and applications, we provide a relatively comprehensive review of the recent trends in cognitive diagnosis models. Further, we discuss future directions that are worthy of exploration. In addition, we release two Python libraries: EduData for easy access to some relevant public datasets we have collected, and EduCDM that implements popular CDMs to facilitate both applications and research purposes.

Yuting Ning, Zhenya Huang, Xin Lin et al.

Understanding mathematical questions effectively is a crucial task, which can benefit many applications, such as difficulty estimation. Researchers have drawn much attention to designing pre-training models for question representations due to the scarcity of human annotations (e.g., labeling difficulty). However, unlike general free-format texts (e.g., user comments), mathematical questions are generally designed with explicit purposes and mathematical logic, and usually consist of more complex content, such as formulas, and related mathematical knowledge (e.g., Function). Therefore, the problem of holistically representing mathematical questions remains underexplored. To this end, in this paper, we propose a novel contrastive pre-training approach for mathematical question representations, namely QuesCo, which attempts to bring questions with more similar purposes closer. Specifically, we first design two-level question augmentations, including content-level and structure-level, which generate literally diverse question pairs with similar purposes. Then, to fully exploit hierarchical information of knowledge concepts, we propose a knowledge hierarchy-aware rank strategy (KHAR), which ranks the similarities between questions in a fine-grained manner. Next, we adopt a ranking contrastive learning task to optimize our model based on the augmented and ranked questions. We conduct extensive experiments on two real-world mathematical datasets. The experimental results demonstrate the effectiveness of our model.

Ziqing Yang, Yiming Cui, Xin Yao et al.

Pre-trained language models achieve superior performance but are computationally expensive. Techniques such as pruning and knowledge distillation have been developed to reduce their sizes and latencies. In this work, we propose a structured pruning method GRAIN (Gradient-based Intra-attention pruning), which performs task-specific pruning with knowledge distillation and yields highly effective models. Different from common approaches that prune each attention head as a whole, GRAIN inspects and prunes intra-attention structures, which greatly expands the structure search space and enables more flexible models. We also propose a gradient separation strategy that reduces the interference of distillation on pruning for a better combination of the two approaches. Experiments on GLUE, SQuAD, and CoNLL 2003 show that GRAIN notably outperforms other methods, especially in the high sparsity regime, and achieves $6\sim7\times$ speedups while maintaining $93\%\sim99\%$ performance. Under extreme compression where only $3\%$ transformer weights remain, the pruned model is still competitive compared to larger models.

Zihang Xu, Ziqing Yang, Yiming Cui et al.

In the field of machine reading comprehension (MRC), existing systems have surpassed the average performance of human beings in many tasks like SQuAD. However, there is still a long way to go when it comes to logical reasoning. Although some methods for it have been put forward, they either are designed in a quite complicated way or rely too much on external structures. In this paper, we proposed IDOL (InDicator-Oriented Logic Pre-training), an easy-to-understand but highly effective further pre-training task which logically strengthens the pre-trained models with the help of 6 types of logical indicators and a logically rich dataset LGP (LoGic Pre-training). IDOL achieves state-of-the-art performance on ReClor and LogiQA, the two most representative benchmarks in logical reasoning MRC, and is proven to be capable of generalizing to different pre-trained models and other types of MRC benchmarks like RACE and SQuAD 2.0 while keeping competitive general language understanding ability through testing on tasks in GLUE. Besides, at the beginning of the era of large language models, we take several of them like ChatGPT into comparison and find that IDOL still shows its advantage.

Liyang He, Zhenya Huang, Jiayu Liu et al.

Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://github.com/hly1998/BRCD.

Xingqi Wang, Yiming Cui, Xin Yao et al. · tsinghua

Large Vision-Language Models (LVLMs) have recently demonstrated remarkable progress, yet hallucination remains a critical barrier, particularly in chart understanding, which requires sophisticated perceptual and cognitive abilities as well as rigorous factual accuracy. While prior work has investigated hallucinations and chart comprehension independently, their intersection remains largely unexplored. To address this gap, we present ChartHal, a benchmark that features a fine-grained taxonomy of hallucination scenarios in chart understanding, along with a human-validated dataset of 1,062 samples. Our evaluation shows that state-of-the-art LVLMs suffer from severe hallucinations on ChartHal, including proprietary models such as GPT-5 and o4-mini, which achieve only 34.46% and 22.79% accuracy, respectively. Further analysis reveals that questions involving information absent from or contradictory to charts are especially likely to trigger hallucinations, underscoring the urgent need for more robust mitigation strategies. Code and data are available at https://github.com/ymcui/ChartHal .

Yiming Cui, Ting Liu, Wanxiang Che et al.

Achieving human-level performance on some of Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, it is necessary to provide both answer prediction and its explanation to further improve the MRC system's reliability, especially for real-life applications. In this paper, we propose a new benchmark called ExpMRC for evaluating the explainability of the MRC systems. ExpMRC contains four subsets, including SQuAD, CMRC 2018, RACE$^+$, and C$^3$ with additional annotations of the answer's evidence. The MRC systems are required to give not only the correct answer but also its explanation. We use state-of-the-art pre-trained language models to build baseline systems and adopt various unsupervised approaches to extract evidence without a human-annotated training set. The experimental results show that these models are still far from human performance, suggesting that the ExpMRC is challenging. Resources will be available through https://github.com/ymcui/expmrc

Wentao Ma, Yiming Cui, Chenglei Si et al.

Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into subword units and make the representation incomplete and fragile. In this paper, we propose a character-aware pre-trained language model named CharBERT improving on the previous methods (such as BERT, RoBERTa) to tackle these problems. We first construct the contextual word embedding for each token from the sequential character representations, then fuse the representations of characters and the subword representations by a novel heterogeneous interaction module. We also propose a new pre-training task named NLM (Noisy LM) for unsupervised character representation learning. We evaluate our method on question answering, sequence labeling, and text classification tasks, both on the original datasets and adversarial misspelling test sets. The experimental results show that our method can significantly improve the performance and robustness of PLMs simultaneously. Pretrained models, evaluation sets, and code are available at https://github.com/wtma/CharBERT

Chenglei Si, Ziqing Yang, Yiming Cui et al.

Machine Reading Comprehension (MRC) is an important testbed for evaluating models' natural language understanding (NLU) ability. There has been rapid progress in this area, with new models achieving impressive performance on various benchmarks. However, existing benchmarks only evaluate models on in-domain test sets without considering their robustness under test-time perturbations or adversarial attacks. To fill this important gap, we construct AdvRACE (Adversarial RACE), a new model-agnostic benchmark for evaluating the robustness of MRC models under four different types of adversarial attacks, including our novel distractor extraction and generation attacks. We show that state-of-the-art (SOTA) models are vulnerable to all of these attacks. We conclude that there is substantial room for building more robust MRC models and our benchmark can help motivate and measure progress in this area. We release our data and code at https://github.com/NoviScl/AdvRACE .

Ziqing Yang, Yiming Cui, Zhipeng Chen et al.

In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing. It works with different neural network models and supports various kinds of supervised learning tasks, such as text classification, reading comprehension, sequence labeling. TextBrewer provides a simple and uniform workflow that enables quick setting up of distillation experiments with highly flexible configurations. It offers a set of predefined distillation methods and can be extended with custom code. As a case study, we use TextBrewer to distill BERT on several typical NLP tasks. With simple configurations, we achieve results that are comparable with or even higher than the public distilled BERT models with similar numbers of parameters. Our toolkit is available through: http://textbrewer.hfl-rc.com

Yiming Cui, Wanxiang Che, Ting Liu et al.

Though the community has made great progress on Machine Reading Comprehension (MRC) task, most of the previous works are solving English-based MRC problems, and there are few efforts on other languages mainly due to the lack of large-scale training data. In this paper, we propose Cross-Lingual Machine Reading Comprehension (CLMRC) task for the languages other than English. Firstly, we present several back-translation approaches for CLMRC task, which is straightforward to adopt. However, to accurately align the answer into another language is difficult and could introduce additional noise. In this context, we propose a novel model called Dual BERT, which takes advantage of the large-scale training data provided by rich-resource language (such as English) and learn the semantic relations between the passage and question in a bilingual context, and then utilize the learned knowledge to improve reading comprehension performance of low-resource language. We conduct experiments on two Chinese machine reading comprehension datasets CMRC 2018 and DRCD. The results show consistent and significant improvements over various state-of-the-art systems by a large margin, which demonstrate the potentials in CLMRC task. Resources available: https://github.com/ymcui/Cross-Lingual-MRC

Qi Liu, Yan Zhuang, Haoyang Bi et al.

Computerized Adaptive Testing (CAT) provides an efficient and tailored method for assessing the proficiency of examinees, by dynamically adjusting test questions based on their performance. Widely adopted across diverse fields like education, healthcare, sports, and sociology, CAT has revolutionized testing practices. While traditional methods rely on psychometrics and statistics, the increasing complexity of large-scale testing has spurred the integration of machine learning techniques. This paper aims to provide a machine learning-focused survey on CAT, presenting a fresh perspective on this adaptive testing method. By examining the test question selection algorithm at the heart of CAT's adaptivity, we shed light on its functionality. Furthermore, we delve into cognitive diagnosis models, question bank construction, and test control within CAT, exploring how machine learning can optimize these components. Through an analysis of current methods, strengths, limitations, and challenges, we strive to develop robust, fair, and efficient CAT systems. By bridging psychometric-driven CAT research with machine learning, this survey advocates for a more inclusive and interdisciplinary approach to the future of adaptive testing.

Tong Xiao, Jiayu Liu, Zhenya Huang et al.

Geometry Problem Solving (GPS), which is a classic and challenging math problem, has attracted much attention in recent years. It requires a solver to comprehensively understand both text and diagram, master essential geometry knowledge, and appropriately apply it in reasoning. However, existing works follow a paradigm of neural machine translation and only focus on enhancing the capability of encoders, which neglects the essential characteristics of human geometry reasoning. In this paper, inspired by dual-process theory, we propose a Dual-Reasoning Geometry Solver (DualGeoSolver) to simulate the dual-reasoning process of humans for GPS. Specifically, we construct two systems in DualGeoSolver, namely Knowledge System and Inference System. Knowledge System controls an implicit reasoning process, which is responsible for providing diagram information and geometry knowledge according to a step-wise reasoning goal generated by Inference System. Inference System conducts an explicit reasoning process, which specifies the goal in each reasoning step and applies the knowledge to generate program tokens for resolving it. The two systems carry out the above process iteratively, which behaves more in line with human cognition. We conduct extensive experiments on two benchmark datasets, GeoQA and GeoQA+. The results demonstrate the superiority of DualGeoSolver in both solving accuracy and robustness from explicitly modeling human reasoning process and knowledge application.

Runxuan Liu, Bei Luo, Jiaqi Li et al.

Large language models (LLMs) have shown remarkable capabilities in natural language processing. However, in knowledge graph question answering tasks (KGQA), there remains the issue of answering questions that require multi-hop reasoning. Existing methods rely on entity vector matching, but the purpose of the question is abstract and difficult to match with specific entities. As a result, it is difficult to establish reasoning paths to the purpose, which leads to information loss and redundancy. To address this issue, inspired by human reverse thinking, we propose Ontology-Guided Reverse Thinking (ORT), a novel framework that constructs reasoning paths from purposes back to conditions. ORT operates in three key phases: (1) using LLM to extract purpose labels and condition labels, (2) constructing label reasoning paths based on the KG ontology, and (3) using the label reasoning paths to guide knowledge retrieval. Experiments on the WebQSP and CWQ datasets show that ORT achieves state-of-the-art performance and significantly enhances the capability of LLMs for KGQA.

Zichong Chen, Shijin Wang, Yang Zhou

Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to learn and apply style representations from a limited set of reference images, enabling content synthesis of both text-aligned and stylistically coherent. Our approach uniquely decomposes style into two components, composition and texture, each learned through different strategies. We then leverage two synthesis branches, each focusing on a corresponding style component, to facilitate effective style blending through shared features without affecting content generation. StyleBlend addresses the common issues of text misalignment and weak style representation that previous methods have struggled with. Extensive qualitative and quantitative comparisons demonstrate the superiority of our approach.

Yuxuan Zhou, Xien Liu, Chenwei Yan et al.

Large language models (LLMs) have demonstrated remarkable performance on various medical benchmarks, but their capabilities across different cognitive levels remain underexplored. Inspired by Bloom's Taxonomy, we propose a multi-cognitive-level evaluation framework for assessing LLMs in the medical domain in this study. The framework integrates existing medical datasets and introduces tasks targeting three cognitive levels: preliminary knowledge grasp, comprehensive knowledge application, and scenario-based problem solving. Using this framework, we systematically evaluate state-of-the-art general and medical LLMs from six prominent families: Llama, Qwen, Gemma, Phi, GPT, and DeepSeek. Our findings reveal a significant performance decline as cognitive complexity increases across evaluated models, with model size playing a more critical role in performance at higher cognitive levels. Our study highlights the need to enhance LLMs' medical capabilities at higher cognitive levels and provides insights for developing LLMs suited to real-world medical applications.

Jiayu Liu, Zhenya Huang, Wei Dai et al.

Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy, which are insufficient for assessing their authentic capabilities. In this paper, we propose \textbf{CogMath}, which comprehensively assesses LLMs' mathematical abilities through the lens of human cognition. Specifically, inspired by psychological theories, CogMath formalizes human reasoning process into 3 stages: \emph{problem comprehension}, \emph{problem solving}, and \emph{solution summarization}. Within these stages, we investigate perspectives such as numerical calculation, knowledge, and counterfactuals, and design a total of 9 fine-grained evaluation dimensions. In each dimension, we develop an ``\emph{Inquiry}-\emph{Judge}-\emph{Reference}'' multi-agent system to generate inquiries that assess LLMs' mastery from this dimension. An LLM is considered to truly master a problem only when excelling in all inquiries from the 9 dimensions. By applying CogMath on three benchmarks, we reveal that the mathematical capabilities of 7 mainstream LLMs are overestimated by 30\%-40\%. Moreover, we locate their strengths and weaknesses across specific stages/dimensions, offering in-depth insights to further enhance their reasoning abilities.

Cheng Cheng, Zhenya Huang, Guanhao Zhao et al.

Automatically generating high-quality mathematical problems that align with educational objectives is a crucial task in NLP-based educational technology. Traditional generation methods focus primarily on textual quality, but they often overlook educational objectives. Moreover, these methods address only single-dimensional, simple question generation, failing to meet complex, multifaceted educational requirements. To address these challenges, we constructed and annotated EduMath, a dataset of 16k mathematical questions with multi-dimensional educational objectives. Based on this dataset, we developed EQGEVAL, which incorporates three evaluation dimensions and is designed to assess the ability of models to generate educational questions. Drawing inspiration from teachers' problem design processes, we propose the Educational Question Planning with self-Reflection (EQPR) method for educational mathematical question generation, following a "plan-evaluate-optimize" approach. Specifically, by combining planning algorithm based on Monte Carlo Tree Search with the generative capabilities of Large Language Models, we continuously optimize questions through iterative feedback. This self-optimization mechanism ensures that the generated questions both fit the educational context and strategically achieve specific basic educational objectives. Through extensive experiments based on EQGEVAL, we have demonstrated that EQPR achieves significant improvements in generating questions that meet multi-dimensional educational objectives.

Huixin Zhong, Yanan Liu, Qi Cao et al.

As large language models (LLMs) integrate into collaborative teams, their social conformity -- the tendency to align with majority opinions -- has emerged as a key concern. In humans, conformity arises from informational influence (rational use of group cues for accuracy) or normative influence (social pressure for approval), with uncertainty moderating this balance by shifting from purely analytical to heuristic processing. It remains unclear whether these human psychological mechanisms apply to LLMs. This study adapts the information cascade paradigm from behavioral economics to quantitatively disentangle the two drivers to investigate the moderate effect. We evaluated nine leading LLMs across three decision-making scenarios (medical, legal, investment), manipulating information uncertainty (q = 0.667, 0.55, and 0.70, respectively). Our results indicate that informational influence underpins the models' behavior across all contexts, with accuracy and confidence consistently rising with stronger evidence. However, this foundational mechanism is dramatically modulated by uncertainty. In low-to-medium uncertainty scenarios, this informational process is expressed as a conservative strategy, where LLMs systematically underweight all evidence sources. In contrast, high uncertainty triggers a critical shift: while still processing information, the models additionally exhibit a normative-like amplification, causing them to overweight public signals (beta > 1.55 vs. private beta = 0.81).

Yanxi Luo, Shijin Wang, Zhongxing Xu et al.

Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. In real-world scenarios, practical factors often lead to uncertain modality missingness. Existing methods for handling modality missingness are based on data reconstruction or common subspace projections. However, these methods neglect the confidence in multimodal combinations and impose constraints on intra-class representation, hindering the capture of modality-specific information and resulting in suboptimal performance. To address these challenges, we propose a Confidence-Aware Self-Distillation (CASD) strategy that effectively incorporates multimodal probabilistic embeddings via a mixture of Student's $t$-distributions, enhancing its robustness by incorporating confidence and accommodating heavy-tailed properties. This strategy estimates joint distributions with uncertainty scores and reduces uncertainty in the student network by consistency distillation. Furthermore, we introduce a reparameterization representation module that facilitates CASD in robust multimodal learning by sampling embeddings from the joint distribution for the prediction module to calculate the task loss. As a result, the directional constraint from the loss minimization is alleviated by the sampled representation. Experimental results on three benchmark datasets demonstrate that our method achieves state-of-the-art performance.

Xinxin You, Xien Liu, Qixin Sun et al.

Recent methodologies utilizing synthetic datasets have aimed to address inconsistent hallucinations in large language models (LLMs); however,these approaches are primarily tailored to specific tasks, limiting their generalizability. Inspired by the strong performance of code-trained models in logic-intensive domains, we propose a novel framework that leverages event-based text to generate corresponding code and employs cyclic training to transfer the logical consistency of code to natural language effectively. Our method significantly reduces inconsistent hallucinations across three leading LLMs and two categories of natural language tasks while maintaining overall performance. This framework effectively alleviates hallucinations without necessitating adaptation to downstream tasks, demonstrating generality and providing new perspectives to tackle the challenge of inconsistent hallucinations.

Xinjie Sun, Qi Liu, Kai Zhang et al.

Cognitive diagnosis (CD) aims to reveal students' proficiency in specific knowledge concepts. With the increasing adoption of intelligent education applications, accurately assessing students' knowledge mastery has become an urgent challenge. Although existing cognitive diagnosis frameworks enhance diagnostic accuracy by analyzing students' explicit response records, they primarily focus on individual knowledge state, failing to adequately reflect the relative ability performance of students within hierarchies. To address this, we propose the Hierarchy Constraint-Aware Cognitive Diagnosis Framework (HCD), designed to more accurately represent student ability performance within real educational contexts. Specifically, the framework introduces a hierarchy mapping layer to identify students' levels. It then employs a hierarchy convolution-enhanced attention layer for in-depth analysis of knowledge concepts performance among students at the same level, uncovering nuanced differences. A hierarchy inter-sampling attention layer captures performance differences across hierarchies, offering a comprehensive understanding of the relationships among students' knowledge state. Finally, through personalized diagnostic enhancement, the framework integrates hierarchy constraint perception features with existing models, improving the representation of both individual and group characteristics. This approach enables precise inference of students' knowledge state. Research shows that this framework not only reasonably constrains changes in students' knowledge states to align with real educational settings, but also supports the scientific rigor and fairness of educational assessments, thereby advancing the field of cognitive diagnosis.

Bo Sun, Baoxin Wang, Yixuan Wang et al.

Recently, much Chinese text error correction work has focused on Chinese Spelling Check (CSC) and Chinese Grammatical Error Diagnosis (CGED). In contrast, little attention has been paid to the complicated problem of Chinese Semantic Error Diagnosis (CSED), which lacks relevant datasets. The study of semantic errors is important because they are very common and may lead to syntactic irregularities or even problems of comprehension. To investigate this, we build the CSED corpus, which includes two datasets. The one is for the CSED-Recognition (CSED-R) task. The other is for the CSED-Correction (CSED-C) task. Our annotation guarantees high-quality data through quality assurance mechanisms. Our experiments show that powerful pre-trained models perform poorly on this corpus. We also find that the CSED task is challenging, as evidenced by the fact that even humans receive a low score. This paper proposes syntax-aware models to specifically adapt to the CSED task. The experimental results show that the introduction of the syntax-aware approach is meaningful.

Ziqing Yang, Yiming Cui, Zhigang Chen et al.

Multilingual pre-trained language models (MPLMs) not only can handle tasks in different languages but also exhibit surprising zero-shot cross-lingual transferability. However, MPLMs usually are not able to achieve comparable supervised performance on rich-resource languages compared to the state-of-the-art monolingual pre-trained models. In this paper, we aim to improve the multilingual model's supervised and zero-shot performance simultaneously only with the resources from supervised languages. Our approach is based on transferring knowledge from high-performance monolingual models with a teacher-student framework. We let the multilingual model learn from multiple monolingual models simultaneously. To exploit the model's cross-lingual transferability, we propose MBLM (multi-branch multilingual language model), a model built on the MPLMs with multiple language branches. Each branch is a stack of transformers. MBLM is trained with the zero-shot-aware training strategy that encourages the model to learn from the mixture of zero-shot representations from all the branches. The results on two cross-lingual classification tasks show that, with only the task's supervised data used, our method improves both the supervised and zero-shot performance of MPLMs.

Baoxin Wang, Qingye Meng, Ziyue Wang et al.

Knowledge graph embedding (KGE) models learn the representation of entities and relations in knowledge graphs. Distance-based methods show promising performance on link prediction task, which predicts the result by the distance between two entity representations. However, most of these methods represent the head entity and tail entity separately, which limits the model capacity. We propose two novel distance-based methods named InterHT and InterHT+ that allow the head and tail entities to interact better and get better entity representation. Experimental results show that our proposed method achieves the best results on ogbl-wikikg2 dataset.

Yiming Cui, Wei-Nan Zhang, Wanxiang Che et al.

Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains unclear, placing an obstacle for further understanding these models. This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final MRC system performance, revealing the potential explainability in PLM-based MRC models. To ensure the robustness of the analyses, we perform our experiments in a multilingual way on top of various PLMs. We discover that passage-to-question and passage understanding attentions are the most important ones in the question answering process, showing strong correlations to the final performance than other parts. Through comprehensive visualizations and case studies, we also observe several general findings on the attention maps, which can be helpful to understand how these models solve the questions.

Ziqing Yang, Yiming Cui, Chenglei Si et al.

Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks. Though there are successful applications of AT on some NLP tasks, the distinguishing characteristics of NLP tasks have not been exploited. In this paper, we aim to apply AT on machine reading comprehension (MRC) tasks. Furthermore, we adapt AT for MRC tasks by proposing a novel adversarial training method called PQAT that perturbs the embedding matrix instead of word vectors. To differentiate the roles of passages and questions, PQAT uses additional virtual P/Q-embedding matrices to gather the global perturbations of words from passages and questions separately. We test the method on a wide range of MRC tasks, including span-based extractive RC and multiple-choice RC. The results show that adversarial training is effective universally, and PQAT further improves the performance.

Ziqing Yang, Wentao Ma, Yiming Cui et al.

Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.

Nan Shao, Yiming Cui, Ting Liu et al.

Retrieving information from correlative paragraphs or documents to answer open-domain multi-hop questions is very challenging. To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose graph-based methods to retrieve them. However, in this paper, we point out the intrinsic defect of such methods. Instead, we propose a new architecture that models paragraphs as sequential data and considers multi-hop information retrieval as a kind of sequence labeling task. Specifically, we design a rewritable external memory to model the dependency among paragraphs. Moreover, a threshold gate mechanism is proposed to eliminate the distraction of noise paragraphs. We evaluate our method on both full wiki and distractor subtask of HotpotQA, a public textual multi-hop QA dataset requiring multi-hop information retrieval. Experiments show that our method achieves significant improvement over the published state-of-the-art method in retrieval and downstream QA task performance.

Haoyang Bi, Haiping Ma, Zhenya Huang et al.

Computerized Adaptive Testing (CAT) is emerging as a promising testing application in many scenarios, such as education, game and recruitment, which targets at diagnosing the knowledge mastery levels of examinees on required concepts. It shows the advantage of tailoring a personalized testing procedure for each examinee, which selects questions step by step, depending on her performance. While there are many efforts on developing CAT systems, existing solutions generally follow an inflexible model-specific fashion. That is, they need to observe a specific cognitive model which can estimate examinee's knowledge levels and design the selection strategy according to the model estimation. In this paper, we study a novel model-agnostic CAT problem, where we aim to propose a flexible framework that can adapt to different cognitive models. Meanwhile, this work also figures out CAT solution with addressing the problem of how to generate both high-quality and diverse questions simultaneously, which can give a comprehensive knowledge diagnosis for each examinee. Inspired by Active Learning, we propose a novel framework, namely Model-Agnostic Adaptive Testing (MAAT) for CAT solution, where we design three sophisticated modules including Quality Module, Diversity Module and Importance Module. Extensive experimental results on two real-world datasets clearly demonstrate that our MAAT can support CAT with guaranteeing both quality and diversity perspectives.

Yiming Cui, Ting Liu, Shijin Wang et al.

With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances. However, the existing works only target on the accuracy of the final predictions and neglect the importance of the explanations for the prediction, which is a big obstacle when utilizing these models in real-life applications to convince humans. In this paper, we propose a self-explainable framework for the machine reading comprehension task. The main idea is that the proposed system tries to use less passage information and achieve similar results compared to the system that uses the whole passage, while the filtered passage will be used as explanations. We carried out experiments on three multiple-choice MRC datasets, and found that the proposed system could achieve consistent improvements over baseline systems. To evaluate the explainability, we compared our approach with the traditional attention mechanism in human evaluations and found that the proposed system has a notable advantage over the latter one.

Nan Shao, Yiming Cui, Ting Liu et al.

Recently, attempting to model texts as graph structure and introducing graph neural networks to deal with it has become a trend in many NLP research areas. In this paper, we investigate whether the graph structure is necessary for multi-hop question answering. Our analysis is centered on HotpotQA. We construct a strong baseline model to establish that, with the proper use of pre-trained models, graph structure may not be necessary for multi-hop question answering. We point out that both graph structure and adjacency matrix are task-related prior knowledge, and graph-attention can be considered as a special case of self-attention. Experiments and visualized analysis demonstrate that graph-attention or the entire graph structure can be replaced by self-attention or Transformers.

Yiming Cui, Wanxiang Che, Wei-Nan Zhang et al.

Story Ending Prediction is a task that needs to select an appropriate ending for the given story, which requires the machine to understand the story and sometimes needs commonsense knowledge. To tackle this task, we propose a new neural network called Diff-Net for better modeling the differences of each ending in this task. The proposed model could discriminate two endings in three semantic levels: contextual representation, story-aware representation, and discriminative representation. Experimental results on the Story Cloze Test dataset show that the proposed model siginificantly outperforms various systems by a large margin, and detailed ablation studies are given for better understanding our model. We also carefully examine the traditional and BERT-based models on both SCT v1.0 and v1.5 with interesting findings that may potentially help future studies.

Yiming Cui, Wei-Nan Zhang, Wanxiang Che et al.

Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks. In this paper, we propose Contextual Recurrent Units (CRU) for enhancing local contextual representations in neural networks. The proposed CRU injects convolutional neural networks (CNN) into the recurrent units to enhance the ability to model the local context and reducing word ambiguities even in bi-directional RNNs. We tested our CRU model on sentence-level and document-level modeling NLP tasks: sentiment classification and reading comprehension. Experimental results show that the proposed CRU model could give significant improvements over traditional CNN or RNN models, including bidirectional conditions, as well as various state-of-the-art systems on both tasks, showing its promising future of extensibility to other NLP tasks as well.

Ziqing Yang, Yiming Cui, Wanxiang Che et al.

Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language processing (NLP), the mechanism behind it is still unclear. In this paper, we aim to apply AT on machine reading comprehension (MRC) and study its effects from multiple perspectives. We experiment with three different kinds of RC tasks: span-based RC, span-based RC with unanswerable questions and multi-choice RC. The experimental results show that the proposed method can improve the performance significantly and universally on SQuAD1.1, SQuAD2.0 and RACE. With virtual adversarial training (VAT), we explore the possibility of improving the RC models with semi-supervised learning and prove that examples from a different task are also beneficial. We also find that AT helps little in defending against artificial adversarial examples, but AT helps the model to learn better on examples that contain more low-frequency words.

Fei Wang, Qi Liu, Enhong Chen et al.

Cognitive diagnosis is a fundamental issue in intelligent education, which aims to discover the proficiency level of students on specific knowledge concepts. Existing approaches usually mine linear interactions of student exercising process by manual-designed function (e.g., logistic function), which is not sufficient for capturing complex relations between students and exercises. In this paper, we propose a general Neural Cognitive Diagnosis (NeuralCD) framework, which incorporates neural networks to learn the complex exercising interactions, for getting both accurate and interpretable diagnosis results. Specifically, we project students and exercises to factor vectors and leverage multi neural layers for modeling their interactions, where the monotonicity assumption is applied to ensure the interpretability of both factors. Furthermore, we propose two implementations of NeuralCD by specializing the required concepts of each exercise, i.e., the NeuralCDM with traditional Q-matrix and the improved NeuralCDM+ exploring the rich text content. Extensive experimental results on real-world datasets show the effectiveness of NeuralCD framework with both accuracy and interpretability.

Zhipeng Chen, Yiming Cui, Wentao Ma et al.

Machine Reading Comprehension (MRC) with multiple-choice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Convolutional Spatial Attention (CSA) model which can better handle the MRC with multiple-choice questions. The proposed model could fully extract the mutual information among the passage, question, and the candidates, to form the enriched representations. Furthermore, to merge various attention results, we propose to use convolutional operation to dynamically summarize the attention values within the different size of regions. Experimental results show that the proposed model could give substantial improvements over various state-of-the-art systems on both RACE and SemEval-2018 Task11 datasets.

Zhipeng Chen, Yiming Cui, Wentao Ma et al.

This paper describes the system which got the state-of-the-art results at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. In this paper, we present a neural network called Hybrid Multi-Aspects (HMA) model, which mimic the human's intuitions on dealing with the multiple-choice reading comprehension. In this model, we aim to produce the predictions in multiple aspects by calculating attention among the text, question and choices, and combine these results for final predictions. Experimental results show that our HMA model could give substantial improvements over the baseline system and got the first place on the final test set leaderboard with the accuracy of 84.13%.

Yiming Cui, Ting Liu, Zhipeng Chen et al.

Reading comprehension has embraced a booming in recent NLP research. Several institutes have released the Cloze-style reading comprehension data, and these have greatly accelerated the research of machine comprehension. In this work, we firstly present Chinese reading comprehension datasets, which consist of People Daily news dataset and Children's Fairy Tale (CFT) dataset. Also, we propose a consensus attention-based neural network architecture to tackle the Cloze-style reading comprehension problem, which aims to induce a consensus attention over every words in the query. Experimental results show that the proposed neural network significantly outperforms the state-of-the-art baselines in several public datasets. Furthermore, we setup a baseline for Chinese reading comprehension task, and hopefully this would speed up the process for future research.