Heejin Do

Junling Wang, Boqi Chen, Heejin Do et al.

AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concepts they are intended to teach. Thus, we introduce equation-to-visual generation, a task that, in contrast to conventional image generation, requires producing pedagogically meaningful visuals from arithmetic equations while precisely preserving their numerical and relational structure. Informed by interviews with teachers and an analysis of educational materials, we construct E2V-Bench, a benchmark spanning four pedagogically grounded visual types, along with automatic metrics for evaluating visual correctness. Our evaluation reveals that recent text-to-image (T2I) models frequently fail on this task, with errors dominated by incorrect object counts and broken relational structure. Building on this, we explore benchmark-guided enhancement strategies. These strategies improve representative models, while the remaining gap calls for stronger numerical and relational grounding in future T2I models.

Heejin Do, Yunsu Kim, Gary Geunbae Lee

Automatic pronunciation assessment is a major component of a computer-assisted pronunciation training system. To provide in-depth feedback, scoring pronunciation at various levels of granularity such as phoneme, word, and utterance, with diverse aspects such as accuracy, fluency, and completeness, is essential. However, existing multi-aspect multi-granularity methods simultaneously predict all aspects at all granularity levels; therefore, they have difficulty in capturing the linguistic hierarchy of phoneme, word, and utterance. This limitation further leads to neglecting intimate cross-aspect relations at the same linguistic unit. In this paper, we propose a Hierarchical Pronunciation Assessment with Multi-aspect Attention (HiPAMA) model, which hierarchically represents the granularity levels to directly capture their linguistic structures and introduces multi-aspect attention that reflects associations across aspects at the same level to create more connotative representations. By obtaining relational information from both the granularity- and aspect-side, HiPAMA can take full advantage of multi-task learning. Remarkable improvements in the experimental results on the speachocean762 datasets demonstrate the robustness of HiPAMA, particularly in the difficult-to-assess aspects.

Heejin Do, Sangwon Ryu, Gary Geunbae Lee

Recent advances in automated essay scoring (AES) have shifted towards evaluating multiple traits to provide enriched feedback. Like typical AES systems, multi-trait AES employs the quadratic weighted kappa (QWK) to measure agreement with human raters, aligning closely with the rating schema; however, its non-differentiable nature prevents its direct use in neural network training. In this paper, we propose Scoring-aware Multi-reward Reinforcement Learning (SaMRL), which integrates actual evaluation schemes into the training process by designing QWK-based rewards with a mean-squared error penalty for multi-trait AES. Existing reinforcement learning (RL) applications in AES are limited to classification models despite associated performance degradation, as RL requires probability distributions; instead, we adopt an autoregressive score generation framework to leverage token generation probabilities for robust multi-trait score predictions. Empirical analyses demonstrate that SaMRL facilitates model training, notably enhancing scoring of previously inferior prompts.

Heejin Do, Shashank Sonkar, Mrinmaya Sachan

Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators. Yet such simulators are typically evaluated by output similarity to real students, not by whether they behave like students with coherent misconceptions during interaction. We introduce a controlled framework for evaluating misconception faithfulness, whether a simulator maintains a misconception-driven belief state and updates selectively when feedback addresses the underlying misconception. Central to our framework is a misconception-contrastive feedback protocol that compares targeted feedback against two controls: misaligned feedback (targeting a different but plausible misconception) and generic feedback (only identifying answer is wrong). We propose Selective Flip Score (SFS), which quantifies how much more often a simulator flips its answer under targeted feedback than under contrastive controls. Across seven LLMs (4B-120B), multiple datasets, and prompting strategies, simulators exhibit near-zero SFS, correcting their answers at similarly high rates regardless of feedback relevance. Further analyses reveal a sycophantic failure mode: models behave less like students with misconceptions but more like problem-solvers who treat any corrective signal as a cue to abandon the simulated belief and re-solve from internal knowledge. To address this, we develop a post-training pipeline spanning supervised fine-tuning (SFT), preference optimization, and reinforcement learning (RL) with an SFS-aligned reward; SFT yields notable gains up to +0.56, and SFS-aligned RL provides more consistent improvements than preference optimization. Our results establish misconception faithfulness as a challenging yet trainable property, motivating a shift from static output matching toward interactive, belief-aware student modeling.

Jinmyeong An, Sangwon Ryu, Heejin Do et al.

Online grooming is a severe social threat where sexual predators gradually entrap child victims with subtle and gradual manipulation. Therefore, timely intervention for online grooming is critical for proactive protection. However, previous methods fail to determine the optimal intervention points (i.e., jump to conclusions) as they rely on chat-level risk labels by causing weak supervision of risky utterances. For timely detection, we propose speed control reinforcement learning (SCoRL) (The code and supplementary materials are available at https://github.com/jinmyeongAN/SCoRL), incorporating a practical strategy derived from luring communication theory (LCT). To capture the predator's turn-level entrapment, we use a turn-level risk label based on the LCT. Then, we design a novel speed control reward function that balances the trade-off between speed and accuracy based on turn-level risk label; thus, SCoRL can identify the optimal intervention moment. In addition, we introduce a turn-level metric for precise evaluation, identifying limitations in previously used chat-level metrics. Experimental results show that SCoRL effectively preempted online grooming, offering a more proactive and timely solution. Further analysis reveals that our method enhances performance while intuitively identifying optimal early intervention points.

Heejin Do, Yunsu Kim, Gary Geunbae Lee

Recently, encoder-only pre-trained models such as BERT have been successfully applied in automated essay scoring (AES) to predict a single overall score. However, studies have yet to explore these models in multi-trait AES, possibly due to the inefficiency of replicating BERT-based models for each trait. Breaking away from the existing sole use of encoder, we propose an autoregressive prediction of multi-trait scores (ArTS), incorporating a decoding process by leveraging the pre-trained T5. Unlike prior regression or classification methods, we redefine AES as a score-generation task, allowing a single model to predict multiple scores. During decoding, the subsequent trait prediction can benefit by conditioning on the preceding trait scores. Experimental results proved the efficacy of ArTS, showing over 5% average improvements in both prompts and traits.

Jun Seo, Sangwon Ryu, Heejin Do et al.

Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with Knowledge Components, they overlook the procedural dynamics of problem solving. We propose Behavior-Aware Item Modeling (BAIM), a framework that enriches item representations by integrating dynamic procedural solution information. BAIM leverages a reasoning language model to decompose each item's solution into four problem-solving stages (i.e., understand, plan, carry out, and look back), pedagogically grounded in Polya's framework. Specifically, it derives stage-level representations from per-stage embedding trajectories, capturing latent signals beyond surface features. To reflect learner heterogeneity, BAIM adaptively routes these stage-wise representations, introducing a context-conditioned mechanism within a KT backbone, allowing different procedural stages to be emphasized for different learners. Experiments on XES3G5M and NIPS34 show that BAIM consistently outperforms strong pretraining-based baselines, achieving particularly large gains under repeated learner interactions.

Wonjun Lee, Solee Im, Heejin Do et al.

Dysarthric speech recognition often suffers from performance degradation due to the intrinsic diversity of dysarthric severity and extrinsic disparity from normal speech. To bridge these gaps, we propose a Dynamic Phoneme-level Contrastive Learning (DyPCL) method, which leads to obtaining invariant representations across diverse speakers. We decompose the speech utterance into phoneme segments for phoneme-level contrastive learning, leveraging dynamic connectionist temporal classification alignment. Unlike prior studies focusing on utterance-level embeddings, our granular learning allows discrimination of subtle parts of speech. In addition, we introduce dynamic curriculum learning, which progressively transitions from easy negative samples to difficult-to-distinguishable negative samples based on phonetic similarity of phoneme. Our approach to training by difficulty levels alleviates the inherent variability of speakers, better identifying challenging speeches. Evaluated on the UASpeech dataset, DyPCL outperforms baseline models, achieving an average 22.10\% relative reduction in word error rate (WER) across the overall dysarthria group.

Subin Kim, Hoonrae Kim, Heejin Do et al.

Previous research has revealed the potential of large language models (LLMs) to support cognitive reframing therapy; however, their focus was primarily on text-based methods, often overlooking the importance of non-verbal evidence crucial in real-life therapy. To alleviate this gap, we extend the textual cognitive reframing to multimodality, incorporating visual clues. Specifically, we present a new dataset called Multi Modal-Cognitive Support Conversation (M2CoSC), which pairs each GPT-4-generated dialogue with an image that reflects the virtual client's facial expressions. To better mirror real psychotherapy, where facial expressions lead to interpreting implicit emotional evidence, we propose a multi-hop psychotherapeutic reasoning approach that explicitly identifies and incorporates subtle evidence. Our comprehensive experiments with both LLMs and vision-language models (VLMs) demonstrate that the VLMs' performance as psychotherapists is significantly improved with the M2CoSC dataset. Furthermore, the multi-hop psychotherapeutic reasoning method enables VLMs to provide more thoughtful and empathetic suggestions, outperforming standard prompting methods.

Heejin Do, Sangwon Ryu, Gary Geunbae Lee

Multi-trait automated essay scoring (AES) systems provide a fine-grained evaluation of an essay's diverse aspects. While they excel in scoring, prior systems fail to explain why specific trait scores are assigned. This lack of transparency leaves instructors and learners unconvinced of the AES outputs, hindering their practical use. To address this, we propose a self-explainable Rationale-Driven Multi-trait automated Essay scoring (RaDME) framework. RaDME leverages the reasoning capabilities of large language models (LLMs) by distilling them into a smaller yet effective scorer. This more manageable student model is optimized to sequentially generate a trait score followed by the corresponding rationale, thereby inherently learning to select a more justifiable score by considering the subsequent rationale during training. Our findings indicate that while LLMs underperform in direct AES tasks, they excel in rationale generation when provided with precise numerical scores. Thus, RaDME integrates the superior reasoning capacities of LLMs into the robust scoring accuracy of an optimized smaller model. Extensive experiments demonstrate that RaDME achieves both accurate and adequate reasoning while supporting high-quality multi-trait scoring, significantly enhancing the transparency of AES.

Heejin Do, Taehee Park, Sangwon Ryu et al.

In automated essay scoring (AES), recent efforts have shifted toward cross-prompt settings that score essays on unseen prompts for practical applicability. However, prior methods trained with essay-score pairs of specific prompts pose challenges in obtaining prompt-generalized essay representation. In this work, we propose a grammar-aware cross-prompt trait scoring (GAPS), which internally captures prompt-independent syntactic aspects to learn generic essay representation. We acquire grammatical error-corrected information in essays via the grammar error correction technique and design the AES model to seamlessly integrate such information. By internally referring to both the corrected and the original essays, the model can focus on generic features during training. Empirical experiments validate our method's generalizability, showing remarkable improvements in prompt-independent and grammar-related traits. Furthermore, GAPS achieves notable QWK gains in the most challenging cross-prompt scenario, highlighting its strength in evaluating unseen prompts.

Sangwon Ryu, Heejin Do, Daehee Kim et al.

Large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks. However, their ability to precisely control summary attributes (e.g., length or topic) remains underexplored, limiting their adaptability to specific user preferences. In this paper, we systematically explore the controllability of LLMs. To this end, we revisit summary attribute measurements and introduce iterative evaluation metrics, failure rate and average iteration count to precisely evaluate controllability of LLMs, rather than merely assessing errors. Our findings show that LLMs struggle more with numerical attributes than with linguistic attributes. To address this challenge, we propose a guide-to-explain framework (GTE) for controllable summarization. Our GTE framework enables the model to identify misaligned attributes in the initial draft and guides it in self-explaining errors in the previous output. By allowing the model to reflect on its misalignment, GTE generates well-adjusted summaries that satisfy the desired attributes with robust effectiveness, requiring surprisingly fewer iterations than other iterative approaches.

Heejin Do, Jaehui Hwang, Dongyoon Han et al.

Evaluating large language models (LLMs) on final-answer correctness is the dominant paradigm. This approach, however, provides a coarse signal for model improvement and overlooks the quality of the underlying reasoning process. We argue that a more granular evaluation of reasoning offers a more effective path to building robust models. We decompose reasoning quality into two dimensions: relevance and coherence. Relevance measures if a step is grounded in the problem; coherence measures if it follows logically from prior steps. To measure these aspects reliably, we introduce causal stepwise evaluation (CaSE). This method assesses each reasoning step using only its preceding context, which avoids hindsight bias. We validate CaSE against human judgments on our new expert-annotated benchmarks, MRa-GSM8K and MRa-MATH. More importantly, we show that curating training data with CaSE-evaluated relevance and coherence directly improves final task performance. Our work provides a scalable framework for analyzing, debugging, and improving LLM reasoning, demonstrating the practical value of moving beyond validity checks.

Sangwon Ryu, Heejin Do, Yunsu Kim et al.

Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interdependence among attributes makes it challenging for language models to satisfy correlated constraints consistently. Moreover, previous approaches often require per-attribute fine-tuning, limiting flexibility across diverse summary attributes. In this paper, we propose adaptive planning for multi-attribute controllable summarization (PACO), a training-free framework that reframes the task as planning the order of sequential attribute control with a customized Monte Carlo Tree Search (MCTS). In PACO, nodes represent summaries, and actions correspond to single-attribute adjustments, enabling progressive refinement of only the attributes requiring further control. This strategy adaptively discovers optimal control orders, ultimately producing summaries that effectively meet all constraints. Extensive experiments across diverse domains and models demonstrate that PACO achieves robust multi-attribute controllability, surpassing both LLM-based self-planning models and fine-tuned baselines. Remarkably, PACO with Llama-3.2-1B rivals the controllability of the much larger Llama-3.3-70B baselines. With larger models, PACO achieves superior control performance, outperforming all competitors.

Taehee Park, Heejin Do, Gary Geunbae Lee

Robust supervised fine-tuned small Language Models (sLMs) often show high reliability but tend to undercorrect. They achieve high precision at the cost of low recall. Conversely, Large Language Models (LLMs) often show the opposite tendency, making excessive overcorrection, leading to low precision. To effectively harness the strengths of LLMs to address the recall challenges in sLMs, we propose Post-Correction via Overcorrection (PoCO), a novel approach that strategically balances recall and precision. PoCO first intentionally triggers overcorrection via LLM to maximize recall by allowing comprehensive revisions, then applies a targeted post-correction step via fine-tuning smaller models to identify and refine erroneous outputs. We aim to harmonize both aspects by leveraging the generative power of LLMs while preserving the reliability of smaller supervised models. Our extensive experiments demonstrate that PoCO effectively balances GEC performance by increasing recall with competitive precision, ultimately improving the overall quality of grammatical error correction.

Heejin Do, Sangwon Ryu, Jonghwi Kim et al.

With the growing demand to fit fine-grained user intents, faceted query-by-example (QBE), which retrieves similar documents conditioned on specific facets, has gained recent attention. However, prior approaches mainly depend on document-level comparisons using basic indicators like citations due to the lack of facet-level relevance datasets; yet, this limits their use to citation-based domains and fails to capture the intricacies of facet constraints. In this paper, we propose a multi-facet blending (FaBle) augmentation method, which exploits modularity by decomposing and recomposing to explicitly synthesize facet-specific training sets. We automatically decompose documents into facet units and generate (ir)relevant pairs by leveraging LLMs' intrinsic distinguishing capabilities; then, dynamically recomposing the units leads to facet-wise relevance-informed document pairs. Our modularization eliminates the need for pre-defined facet knowledge or labels. Further, to prove the FaBle's efficacy in a new domain beyond citation-based scientific paper retrieval, we release a benchmark dataset for educational exam item QBE. FaBle augmentation on 1K documents remarkably assists training in obtaining facet conditional embeddings.

Chaebin Lee, Seungyeon Seo, Heejin Do et al.

With the advancement of chatbots and the growing demand for automatic depression detection, identifying depression in patient conversations has gained more attention. However, prior methods often assess depression in a binary way or only a single score without diverse feedback and lack focus on enhancing dialogue responses. In this paper, we present a novel task of multi-aspect depression severity assessment via an inductive dialogue system (MaDSA), evaluating a patient's depression level on multiple criteria by incorporating an assessment-aided response generation. Further, we propose a foundational system for MaDSA, which induces psychological dialogue responses with an auxiliary emotion classification task within a hierarchical severity assessment structure. We synthesize the conversational dataset annotated with eight aspects of depression severity alongside emotion labels, proven robust via human evaluations. Experimental results show potential for our preliminary work on MaDSA.

Heejin Do, Wonjun Lee, Gary Geunbae Lee

In automated pronunciation assessment, recent emphasis progressively lies on evaluating multiple aspects to provide enriched feedback. However, acquiring multi-aspect-score labeled data for non-native language learners' speech poses challenges; moreover, it often leads to score-imbalanced distributions. In this paper, we propose two Acoustic Feature Mixup strategies, linearly and non-linearly interpolating with the in-batch averaged feature, to address data scarcity and score-label imbalances. Primarily using goodness-of-pronunciation as an acoustic feature, we tailor mixup designs to suit pronunciation assessment. Further, we integrate fine-grained error-rate features by comparing speech recognition results with the original answer phonemes, giving direct hints for mispronunciation. Effective mixing of the acoustic features notably enhances overall scoring performances on the speechocean762 dataset, and detailed analysis highlights our potential to predict unseen distortions.

Sangwon Ryu, Heejin Do, Yunsu Kim et al.

Remarkable advances in large language models (LLMs) have enabled high-quality text summarization. However, this capability is currently accessible only through LLMs of substantial size or proprietary LLMs with usage fees. In response, smaller-scale LLMs (sLLMs) of easy accessibility and low costs have been extensively studied, yet they often suffer from missing key information and entities, i.e., low relevance, in particular, when input documents are long. We hence propose a key-element-informed instruction tuning for summarization, so-called KEITSum, which identifies key elements in documents and instructs sLLM to generate summaries capturing these key elements. Experimental results on dialogue and news datasets demonstrate that sLLM with KEITSum indeed provides high-quality summarization with higher relevance and less hallucinations, competitive to proprietary LLM.

Sangwon Ryu, Heejin Do, Yunsu Kim et al.

The evaluation of summary quality encompasses diverse dimensions such as consistency, coherence, relevance, and fluency. However, existing summarization methods often target a specific dimension, facing challenges in generating well-balanced summaries across multiple dimensions. In this paper, we propose multi-objective reinforcement learning tailored to generate balanced summaries across all four dimensions. We introduce two multi-dimensional optimization (MDO) strategies for adaptive learning: 1) MDO_min, rewarding the current lowest dimension score, and 2) MDO_pro, optimizing multiple dimensions similar to multi-task learning, resolves conflicting gradients across dimensions through gradient projection. Unlike prior ROUGE-based rewards relying on reference summaries, we use a QA-based reward model that aligns with human preferences. Further, we discover the capability to regulate the length of summaries by adjusting the discount factor, seeking the generation of concise yet informative summaries that encapsulate crucial points. Our approach achieved substantial performance gains compared to baseline models on representative summarization datasets, particularly in the overlooked dimensions.

Heejin Do, Yunsu Kim, Gary Geunbae Lee

Automated essay scoring (AES) aims to score essays written for a given prompt, which defines the writing topic. Most existing AES systems assume to grade essays of the same prompt as used in training and assign only a holistic score. However, such settings conflict with real-education situations; pre-graded essays for a particular prompt are lacking, and detailed trait scores of sub-rubrics are required. Thus, predicting various trait scores of unseen-prompt essays (called cross-prompt essay trait scoring) is a remaining challenge of AES. In this paper, we propose a robust model: prompt- and trait relation-aware cross-prompt essay trait scorer. We encode prompt-aware essay representation by essay-prompt attention and utilizing the topic-coherence feature extracted by the topic-modeling mechanism without access to labeled data; therefore, our model considers the prompt adherence of an essay, even in a cross-prompt setting. To facilitate multi-trait scoring, we design trait-similarity loss that encapsulates the correlations of traits. Experiments prove the efficacy of our model, showing state-of-the-art results for all prompts and traits. Significant improvements in low-resource-prompt and inferior traits further indicate our model's strength.

Heejin Do, Yunsu Kim, Gary Geunbae Lee

With rapid technological growth, automatic pronunciation assessment has transitioned toward systems that evaluate pronunciation in various aspects, such as fluency and stress. However, despite the highly imbalanced score labels within each aspect, existing studies have rarely tackled the data imbalance problem. In this paper, we suggest a novel loss function, score-balanced loss, to address the problem caused by uneven data, such as bias toward the majority scores. As a re-weighting approach, we assign higher costs when the predicted score is of the minority class, thus, guiding the model to gain positive feedback for sparse score prediction. Specifically, we design two weighting factors by leveraging the concept of an effective number of samples and using the ranks of scores. We evaluate our method on the speechocean762 dataset, which has noticeably imbalanced scores for several aspects. Improved results particularly on such uneven aspects prove the effectiveness of our method.