Papers by Heejin Kim
Transparent Reference-free Automated Evaluation of Open-Ended User Survey Responses (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods to evaluate open-ended survey responses are expensive and lack ground-truth reference for comparison. |
| Approach: | They propose a two-stage evaluation framework specifically designed for human survey responses that uses gibberish filtering to remove nonsensical responses. |
| Outcome: | The proposed evaluation framework outperforms existing metrics on English and Korean datasets and shows strong correlations with expert assessment. |
Autoregressive Score Generation for Multi-trait Essay Scoring (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing holistic approaches to score essays using pre-trained BERT-based models are inefficient, leading to inferior qualities in data-scarce traits. |
| Approach: | They propose an autoregressive prediction of multi-trait scores using pre-trained T5 models. |
| Outcome: | The proposed model shows over 5% improvement in prompts and traits compared to previous models . |
Revisiting Early Detection of Sexual Predators via Turn-level Optimization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to detect online grooming rely on chat-level risk labels and fail to identify optimal intervention points. |
| Approach: | They propose a speed control reinforcement learning strategy based on luring communication theory to capture the predator’s turn-level entrapment and a new reward function that balances the trade-off between speed and accuracy based upon the LCT. |
| Outcome: | The proposed method preempts online grooming while identifying optimal early intervention points. |
Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent trends in LLMs development show growing interest in the use and application of sovereign LLM models. |
| Approach: | They propose a framework for extracting and evaluating socio-cultural elements of sovereign LLMs and assess their technical robustness. |
| Outcome: | The proposed framework assesses the socio-cultural elements of sovereign LLMs and their technical robustness. |
Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search (2026.acl-long)
Copied to clipboard
| Challenge: | Controllable summarization is a form of outputs that tailors summaries to user-specified attributes. |
| Approach: | They propose an adaptive planning framework that reframes the task as planning the order of sequential attribute control with a customized Monte Carlo Tree Search. |
| Outcome: | The proposed framework surpasses LLM-based self-planning models and fine-tuned baselines in multi-attribute controllable summarization. |
Multi-Facet Blending for Faceted Query-by-Example Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to faceted query-by-example (QBE) rely on document-level comparisons using basic indicators like citations . however, this limited their use to citation-based domains and fails to capture the intricacies of facet constraints. |
| Approach: | They propose a multi-facet blending augmentation method that exploits modularity by decomposing and recomposing to synthesize facet-specific training sets. |
| Outcome: | The proposed method decomposes documents into facet units and generates (ir)relevant pairs, thereby synthesizing facet-specific training sets. |
Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on text-based cognitive reframing, but neglected the importance of non-verbal evidence in real-life therapy. |
| Approach: | They propose a dataset that pairs each GPT-4-generated dialogue with an image that reflects the virtual client’s facial expressions to better mirror real psychotherapy, where facial expression leads to interpreting implicit emotional evidence. |
| Outcome: | The proposed approach outperforms existing methods with LLMs and vision-language models and provides more thoughtful and empathetic suggestions. |
DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on data augmentation and feature extraction methods to improve dysarthric speech recognition. |
| Approach: | They propose a Dynamic Phoneme-level Contrastive Learning method which decomposes the speech utterance into phoneme segments for phoneme- level contrastive learning. |
| Outcome: | The proposed method outperforms baseline models and achieves an average 22.10% reduction in word error rate (WER) across the overall dysarthria group. |
Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing summarization methods target a specific dimension, resulting in poor quality summaries. |
| Approach: | They propose multi-objective reinforcement learning tailored to generate balanced summaries across all dimensions. |
| Outcome: | The proposed model achieves significant performance gains compared to baseline models on representative summarization datasets on four dimensions. |
Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that the current de-identification process is inadequate for court judgments at scale . |
| Approach: | They propose a framework for de-identification that aligns with relevant laws and practices . they construct and release the first Korean legal dataset containing annotated judgments . |
| Outcome: | The proposed framework achieves state-of-the-art in the de-identification of court judgments. |
FillerSpeech: Towards Human-Like Text-to-Speech Synthesis with Filler Insertion and Filler Style Control (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in speech synthesis have improved audio quality and pronunciation . fillers are an integral part of natural human conversation, but achieving human-like conversational speech remains a challenge. |
| Approach: | They propose a speech synthesis framework that enables natural filler insertion and style control . they propose 'filler-inclusive' speech data that includes fillers with pitch and duration information . |
| Outcome: | The proposed framework enables natural filler insertion and style control . the proposed framework is validated and can be used to predict filler style . |
Exploring Iterative Controllable Summarization with Large Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) excel at abstractive summarization tasks, but their ability to precisely control summary attributes remains underexplored. |
| Approach: | They propose a guide-to-explain framework for controllable summarization that enables the model to identify misaligned attributes in the initial draft and guides it to self-explan errors in the previous output. |
| Outcome: | The proposed framework generates well-adjusted summaries that satisfy the desired attributes with robust effectiveness while requiring surprisingly fewer iterations than other iterative approaches. |
How Positive Are You: Text Style Transfer using Adaptive Style Embedding (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches for unsupervised text style transfer are disentanglement between content and style. |
| Approach: | They propose to separate a model with a sentence reconstruction module and a style module to improve model architecture. |
| Outcome: | The proposed method improves style transfer performance and content preservation . the proposed method can be used to modify a sentence with a specified style attribute . |
Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing systems assume to grade essays on same prompt as used in training and assign only a holistic score. |
| Approach: | They propose a prompt- and trait relation-aware cross-prompt essay trait scorer that encodes prompt-awful essay representation by essay-promotion attention and utilizing the topic-coherence feature extracted by the topic model. |
| Outcome: | The proposed model shows state-of-the-art results for all prompts and traits. |
Empowering Retrieval-based Conversational Recommendation with Contrasting User Preferences (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing CRSs assume positive and negative user preferences, but assume that the entities in the dialogue history are positive. |
| Approach: | They propose a conversational recommender model that captures user sentiments and uses the reasoning capacity of the LLMs to extract user's hidden preferences. |
| Outcome: | The proposed model outperforms existing methods in three benchmark datasets, improving up to 99.72% in Recall@10. |
Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing (2026.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Tracing (KT) aims to predict learners’ future performance from past interactions, but they overlook the procedural dynamics of problem solving. |
| Approach: | They propose a framework that enriches item representations by integrating dynamic procedural solution information. |
| Outcome: | Experiments on XES3G5M and NIPS34 show that BAIM outperforms strong pretraining-based baselines, achieving particularly large gains under repeated learner interactions. |