Papers by Min Kim
Jamendo-MT-QA: A Benchmark for Multi-Track Comparative Music Question Answering (2026.findings-acl)
Copied to clipboard
Junyoung Koh, Jaeyun Lee, Soo Yong Kim, Gyu Hyeong Choi, Jung In Koh, Jordan Phillips, Yeonjin Lee, Min Song
| Challenge: | Existing benchmarks for music question answering do not systematically evaluate reasoning across tracks. |
| Approach: | They propose a dataset and benchmark for multi-track comparative question answering . they construct 36,519 comparative QA items over 12,173 track pairs . |
| Outcome: | The proposed dataset and benchmark for multi-track comparative question answering is based on the Jamendo-QA dataset. |
Dual Process Masking for Dialogue Act Recognition (2024.findings-emnlp)
Copied to clipboard
Yeo Jin Kim, Halim Acosta, Wookhee Min, Jonathan Rowe, Bradford Mott, Snigdha Chaturvedi, James Lester
| Challenge: | Dialogue act recognition is the task of classifying conversational utterances based on their communicative intent or function. |
| Approach: | They propose a dual-processing approach that masks less important tokens in the input and enhances interpretability by using the masks applied during classification learning. |
| Outcome: | The proposed approach significantly improves performance over strong baselines for dialogue act recognition on a collaborative problem-solving dataset and three public dialogue benchmarks. |
An Empirical Study of Group Conformity in Multi-Agent Systems (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning. |
| Approach: | They analyze how LLM agents shape public opinion through debates on five contentious topics by simulating over 2,500 debates. |
| Outcome: | The proposed models show that LLM agents adopt specific stances over time and align with numerically dominant groups or more intelligent agents, exerting a greater influence. |
PanicToCalm: A Proactive Counseling Agent for Panic Attacks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for training such models are limited due to ethical and logistical issues. |
| Approach: | They propose a dataset that includes high-distress episodes constructed from first-person narratives and structured around the principles of Psychological First Aid. |
| Outcome: | The proposed model outperforms baseline models in counselor-side metrics and client affect improvement. |
Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation (2025.emnlp-main)
Copied to clipboard
| Challenge: | a recent study has found that large vision–language models are vulnerable to visual biases that inflate scores without altering semantic content. |
| Approach: | They propose a novel meta-evaluation benchmark that exhibits diverse score distributions. |
| Outcome: | The proposed model exhibits vulnerability across all domains, and combines multiple biases amplifies their effects, and pairwise evaluations are similarly susceptible. |
MILD Bot: Multidisciplinary Childhood Cancer Survivor Question-Answering Bot (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing systems in the United States provide limited psychosocial support for childhood cancer survivors due to stigma and disclosing medical history. |
| Approach: | They propose a multidisciplinary chILDhood cancer survivor question-answering bot that uses an intent classifier and a semantic textual similarity model to provide timely, accurate, and high-quality information. |
| Outcome: | The proposed model shows significant promise in offering timely, accurate, and high-quality information, effectively addressing a critical need for support among childhood cancer survivors. |
Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts (2025.emnlp-main)
Copied to clipboard
Yuho Lee, Jiaqi Deng, Nicole Hee-Yeon Kim, Hyangsuk Min, Taewon Yun, Minjeong Ban, Kim Yul, Hwanjun Song
| Challenge: | HAMLET is a framework for evaluating the long-context comprehension of large language models. |
| Approach: | They propose a framework for evaluating the long-context comprehension of large language models . HAMLET structures key information of source texts into a three-level hierarchy . |
| Outcome: | HAMLET achieves 90% agreement with expert judgments while reducing evaluation cost by up to 25. |
Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Vision-Language Models (LVLMs) generate detailed and coherent responses from visual inputs but are prone to generate hallucinations due to an over-reliance on language priors. |
| Approach: | They propose a method that reduces the text context and controls only the image-related POS tokens to maintain text quality by reducing the text contextualization. |
| Outcome: | The proposed method achieves state-of-the-art performance on object hallucination benchmarks and achieves Pareto optimality among the existing methods. |
sudo rm -rf agentic_security (2025.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used as computer-use agents . authors present a novel attack framework that bypasses refusal-trained safeguards . |
| Approach: | They propose a new attack framework that bypasses refusal-trained safeguards in LLMs . SUDO iteratively refines its attacks based on a built-in refusal feedback . authors highlight need for robust, context-aware safeguards if LLM is to be used . |
| Outcome: | The proposed framework bypasses refusal-trained safeguards in commercial agents . it achieves a stark attack success rate of 24.41% (with no refinement) and up to 41.33% (by iterative refinement). |
Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal UNcommonsense (MUN) is a benchmark designed to evaluate models’ ability to handle scenarios that deviate from typical visual or contextual expectations. |
| Approach: | They propose a retrieval-based in-context learning framework that transfers reasoning capabilities from larger models to smaller ones without additional training. |
| Outcome: | The proposed method improves on baseline ICL methods by 8.3% over previous methods. |
Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Self-consistency improves reasoning reliability but incurs substantial inference cost . Adaptive self-consistent methods rely on count-based stopping rules that treat all responses equally . |
| Approach: | They propose a method that reframs adaptive sampling from response counting to evidence sufficiency by leveraging response-level confidence. |
| Outcome: | The proposed method reduces inference cost by up to 70% while preserving accuracy on GSM8K. |
Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory (2024.findings-emnlp)
Copied to clipboard
Suyeon Lee, Sunghwan Kim, Minju Kim, Dongjin Kang, Dongil Yang, Harim Kim, Minseok Kang, Dayi Jung, Min Kim, Seungbeen Lee, Kyong-Mee Chung, Youngjae Yu, Dongha Lee, Jinyoung Yeo
| Challenge: | Existing models that use large language models are not available due to ethical concerns, and data privacy concerns are a concern. |
| Approach: | They propose a multi-turn dialogue dataset that emulates real-life counseling interactions using the goal-oriented approach of Cognitive Behavioral Therapy (CBT). |
| Outcome: | The proposed model outperforms other models in counseling skills, highlighting its effectiveness and potential as a counseling agent. |
A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | a study shows that DWT can be effective in the vision domain and natural language processing pre-training stages. |
| Approach: | They examine three key factors to optimize Distillation from Weak Teacher (DWT) DWT is a method of transferring knowledge from a weaker teacher model to a larger student model to improve its performance. |
| Outcome: | a new study examines three key factors to optimize DWT in NLP pre-training scenarios . the impact of teacher model quality and guidelines for adjusting the weighting value for DW T loss are examined . |
PhaseMI: A Motivational Interviewing Dataset for Enhancing Phase Progression in LLM-based Counseling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing MI datasets do not explicitly model structured progression of MI phases, which is essential for effective and goal-oriented counseling. |
| Approach: | They propose a phase-structured MI dataset with a data generation framework that employs therapist, client, and supervisor LLMs to explicitly control phase transitions. |
| Outcome: | The proposed model achieves 12.3% better coverage of MI phases, 37.6% in guiding, and 61.1% in choosing. |
Korean-Specific Dataset for Table Question Answering (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing question answering systems mainly focus on text data, but few Korean datasets exist . a dataset for table question answering is written in English, but it lacks Korean-specific datasets . |
| Approach: | They construct Korean-specific datasets for table question answering using crowd-sourced workers . they then fine-tune the model with these datasets and report the evaluation results . |
| Outcome: | The proposed model is based on Korean datasets and is publicly available . the model is evaluated against other datasets from Korean question answering systems . |
Belief in Authority: Impact of Authority in Multi-Agent Evaluation Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-agent systems utilizing large language models assign authoritative roles to improve performance, yet the impact of authority bias on agent interactions remains underexplored. |
| Approach: | They propose to classify authoritative roles into legitimate, referent, and expert types and analyze their influence across 12-turn conversations using French and Raven’s power-based theory. |
| Outcome: | The proposed model enables agents to perform better in multi-agent evaluations. |
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages (2025.acl-long)
Copied to clipboard
Hyangsuk Min, Yuho Lee, Minjeong Ban, Jiaqi Deng, Nicole Hee-Yeon Kim, Taewon Yun, Hang Su, Jason Cai, Hwanjun Song
| Challenge: | Existing evaluation frameworks for text summarization lack domain-specific assessment criteria and are predominantly English-centric. |
| Approach: | They propose a multi-dimensional, multi-domain evaluation of summarization in English and Chinese that incorporates specialized assessment criteria for each domain and leverages a debate system to enhance annotation quality. |
| Outcome: | The proposed evaluation framework provides a multi-dimensional, multi-domain evaluation of summarization in English and Chinese. |
Co-training and Co-distillation for Quality Improvement and Compression of Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge Distillation (KD) compresses expensive pre-trained language models . however, most smaller models fail to surpass performance of larger model . |
| Approach: | They propose a framework that co-trains two models while mutually distilling knowledge to improve performance and inference speed together. |
| Outcome: | The proposed framework outperforms the original larger model by 1.66 on the GLUE benchmark. |