Publications

[P] = Preprint,  [C] = Conferences , [W] = Workshops, [B] = Books, [D] = Domestic Conferences

2026

[C] QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning

• Doyeon Lee, Eunyi Lyou, Hyunsoo Cho*, Sookyung Kim*, Joonseok Lee*, Jaemoo Choi*  (Co-corresponding)

• The 43rd International Conference on Machine Learning (ICML 2026)

[C] When Prompting Fails to Sway: Inertia in Moral and Value Judgments of Large Language Models

• Bruce W. Lee, Yeongheon Lee, Hyunsoo Cho

• The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)

[C] CUB: Benchmarking Context Utilisation Techniques for Language Models

• Lovisa Hagström, Youna Kim, Haeun Yu, Sang-goo Lee, Richard Johansson, Hyunsoo Cho, Isabelle Augenstein

• The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)

[C] A More Word-like Image Tokenization for MLLMs

• Hyun Lee, Hyemin Jeong, Yejin Kim, Hyungwook Choi, Hyunsoo Cho*, Soo Kyung Kim*, Joonseok Lee*
  (* Co-corresponding)

• The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026)

2025

[W] CountSteer: Steering Attention for Object Counting in Diffusion Models

• Hyemin Boo, Hyoryung Kim, Myungjin Lee, Seunghyeon Lee, Jiyoung Lee, Jang-Hwan Choi, Hyunsoo Cho

• RSD @ AAAI 2026

[C] GOODLIAR: A Reinforcement Learning-Based Deceptive Agent for Disrupting LLM Beliefs on Foundational Principles

• Sookyung Kim, Hyunsoo Cho

• Findings of the Association for Computational Linguistics: ACL 2025 (ACL Findings 2025)

[W] Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs [paper]

• Minsuh Joo, Hyunsoo Cho

• GEM2 Workshop: Generation, Evaluation & Metrics (GEM2 @ ACL 2025)

[B] Foundations of LLMs and Financial Applications

• Yoonseo Chung, Jeonghyun Kim, MiYeon Kim, Minsuh Joo, Hyunsoo Cho

• Finance and Large Language Models, Springer Nature , ISBN: 978-981-96-5832-9

2024

[C] Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts  [paper]

• Youna Kim, Hyuhng Joon Kim, Cheonbok Park, Choonghyun Park, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim

• Findings of the Association for Computational Linguistics: EMNLP 2024 (EMNLP Findings 2024)

[C] Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model [paper]

• Hyunsoo Cho

• Findings of the Association for Computational Linguistics: ACL 2024 (ACL Findings 2024)

[C] Instruction Tuning with Human Curriculum [paper]

• Hyunsoo Cho *, Bruce W. Lee *, Kang Min Yoo (* Equal contributions)

• Findings of the Association for Computational Linguistics: NAACL 2024 (NAACL Findings 2024)

[P] HyperCLOVA X Technical Report [paper]

• HyperCLOVA X Team (Including Hyunsoo Cho)

2023

[P] Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection [paper]

• Choonghyun Park, Hyuhng Joon Kim, Youna Kim, Junyeob Kim, Taeuk Kim, Hyunsoo Cho, Sang-goo Lee, Kang Min Yoo 

[C] Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP [paper]

• Hyuhng Joon Kim, Hyunsoo Cho, Sang-Woo Lee, Junyeob Kim, Choonghyun Park, Sang-goo Lee, Kang Min Yoo, Taeuk Kim.

• Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP Findings 2023)

[C] Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning [paper]

• Hyunsoo Cho, Choonghyun Park, Junyeop Kim, Hyuhng Joon Kim, Kang Min Yoo, Sang-goo Lee

• The 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)

[C] CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels [paper]

• Hyunsoo Cho,Youna Kim, Sang-goo Lee

• The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)

[C] Prompt-Augmented Linear Probing: Scaling Beyond The Limit of Few-shot In-Context Learners [paper]

• Hyunsoo Cho, Hyuhng Joon Kim, Junyeob Kim, Sang-Woo Lee, Sang-goo Lee, Kang Min Yoo, Taeuk Kim

• Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023)

Before 2022