Publications

Under Review

Belief-Shift Reward: Sculpting the Flat Reward Landscape via Telescoping Information Gain. Keonwoo Kim Α, Jaehee Kim, Dongyoon Han, Haanju Yoo Ω. Under review, 2026.
A Domain-Specialized Framework for Semantic Embedding and Retrieval of Semiconductor Equipment Logs. Jihoon Nam Α, Jaehee Kim, Pilsung Kang Ω. Under review, 2026.

AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs. Jaehee Kim Α, Pilsung Kang Ω. International Conference on Machine Learning (ICML), 2026.
FindCoResearcher: A Retrieval-based Collaborative Researcher Recommendation System. Siyeol Sung Α, Jaehee Kim, Jaewon Cheon, Junyoung Son, Pilsung Kang Ω. Korean Institute of Industrial Engineers, 52(1), 55-69.

CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists. Yukyung Lee Α, JoongHoon Kim, Jaehee Kim, Hyowon Cho, Jaewook Kang, Pilsung Kang Ω, Najoung Kim Ω. EMNLP 2025.
Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoning. Joonwon Jang Α, Jaehee Kim, Wonbin Kweon, Seonghyeon Lee, Hwanjo Yu Ω. ACL 2025.

A Gradient Accumulation Method for Dense Retriever under Memory Constraint. Jaehee Kim Α, Yukyung Lee, Pilsung Kang Ω. NeurIPS 2024.
Development of an Unsupervised Learning-Based Fake News Generation Framework and Study the Effectiveness of Dataset Quality Evaluation Metrics. Joonghoon Kim Α, Saeran Park, Jiyoon Lee, Jaehee Kim, Pilsung Kang Ω. Korean Institute of Industrial Engineers, 50(1), 36-44.
CheckEval: Robust Evaluation Framework using Large Language Model via Checklist. Yukyung Lee Α, Joonghoon Kim Α, Jaehee Kim, Hyowon Cho, and Pilsung Kang Ω. CHI 2024 Workshop on Human-centered Evaluation and Auditing of Language Models.

Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification. Yookyung Kho Α, Jaehee Kim, Pilsung Kang Ω. Findings of EMNLP 2023.
Painsight: An Extendable Opinion Mining Framework for Detecting Pain Points Based on Online Customer Reviews. Yukyung Lee Α, Jaehee Kim, Doyoon Kim, Yookyung Kho, Younsun Kim, Pilsung Kang Ω. ACL 2023 13th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (Oral).

REVECA - Rich Encoder-decoder framework for Video Event Captioner. Jaehyuk Heo Α, YongGi Jeong, Sunwoo Kim, Jaehee Kim, Pilsung Kang Ω. CVPR 2022 Workshop on LOng-form VidEo Understanding Challenge.

Α: First author, Ω: Corresponding author