ChaeHun Park (박채훈)

Work Experience 🏢

2025.04 - present: Staff Engineer at Samsung Research

2020.03 - 2020.08: Research Intern at Scatter Lab

2017.07 - 2018.02: Intern at Nota Inc. 

Publications  (*: equal contribution)

Dialogue Evaluation

The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators

Hawon Jeong*, ChaeHun Park*, Jimin Hong, Hojoon Lee and Jaegul Choo

BlackboxNLP@EMNLP2025 (accepted)

[paper]

Speech Recognition

Evaluating and Improving Automatic Speech Recognition Systems for Korean Meteorological Experts

ChaeHun Park, Hojun Cho, Jaegul Choo

Findings of EMNLP 2025 (accepted)

[paper] [data]

Diffusion LLM

Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs

Daehoon Gwak*, Minseo Jung*, Junwoo Park, Minho Park, ChaeHun Park, Junha Hyung, and Jaegul Choo

EMNLP 2025 (accepted)

[paper]

Dataset Generation   Multimodal   Multicultural

Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration

ChaeHun Park*, Yujin Baek*, Jaeseok Kim, Yu-Jung Heo, Du-Seong Chang, and Jaegul Choo

ACL 2025

[paper] [code] [data]

Unlearning

Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning

Minseok Choi, ChaeHun Park, Dohyun Lee, Jaegul Choo

arXiv Preprint (2024.10)

[paper]

Dataset Generation   Event Prediction

Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling

Daehoon Gwak, Junwoo Park, Minho Park, ChaeHun Park, Hyunchan Lee, Edward Choi, Jaegul Choo

Findings of EMNLP2024

[paper]

Tool+LLM

Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?

Seungbin Yang*, ChaeHun Park*, Taehee Kim, and Jaegul Choo

arXiv Preprint (2024.06) 

[paper] [data]

Dialogue Evaluation

PAIREVAL: Open-domain Dialogue Evaluation with Pairwise Comparison

ChaeHun Park, Minseok Choi, Dohyun Lee, and Jaegul Choo

COLM 2024

[paper] [code]

Multimodal  Multilingual

Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering

ChaeHun Park*, Koanho Lee*, Hyesu Lim, Jaeseok Kim, Junmo Park, Yu-Jung Heo, Du-Seong Chang, Jaegul Choo

Findings of ACL2024

[paper]

Language Generation

Learning to Diversify Neural Text Generation via Degenerative Model

Jimin Hong*, ChaeHun Park*, and Jaegul Choo

Findings of IJCNLP-AACL2023 

[paper]

Dialogue Evaluation

DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation

ChaeHun Park, Seungil Lee, Daniel Rim and Jaegul Choo

Findings of ACL2023 

[paper] [code]

Style Transfer

Rethinking Style Transformer by Energy-based Interpretation: Adversarial Unsupervised Style Transfer using Pretrained Model

Hojun Cho, Dohee Kim, Seungwoo Ryu, ChaeHun Park, Hyungjong Noh, Jeong-in Hwang, Minseok Choi, Edward Choi, and Jaegul Choo

EMNLP2022 

[paper] [code]

Dialogue Evaluation  Dataset Generation

Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task

Nyoungwoo Lee, ChaeHun Park, Ho-Jin Choi, and Jaegul Choo

EMNLP2022

[paper] [code]

Dataset Generation

Reweighting Strategy based on Synthetic Data Identification for Sentence Similarity

TaeHee Kim*, ChaeHun Park*, Jimin Hong, Radhika Dua, Edward Choi, and Jaegul Choo

COLING2022 

[paper] [code]

Dialogue Evaluation 

Evaluating Predictive Uncertainty under Distributional Shift on Dialogue Dataset

Nyoungwoo Lee, ChaeHun Park, and Ho-Jin Choi

arXiv Preprint (2021.09)

[paper]

Document Retrieval   Dataset Generation

Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

Soyeong Jeong, Jinheon Baek, ChaeHun Park, and Jong C. Park

SDP2021, A workshop at NAACL-HLT 2021 

[paper] [code]

Dialogue Evaluation   Dataset Generation

Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation Model

ChaeHun Park, Eugene Jang, Wonsuk Yang and Jong C. Park

NAACL-HLT 2021 

[paper] [code]

Argument Mining

Generating Sentential Arguments from Diverse Perspectives on Controversial Topic

ChaeHun Park, Wonsuk Yang and Jong C. Park

NLP4IF 2019, A workshop at EMNLP-IJCNLP 2019 

[paper] [code]

Argument Mining

A Corpus of Sentence-level Annotations of Local Acceptability with Reasons

Wonsuk Yang, Jung Ho Kim, Seungwon Yoon, ChaeHun Park and Jong C. Park

PACLIC 33, 2019

[paper]

Education 🏫

Korea Advanced Institute of Science and Technology (KAIST)

2020.09 - 2025.02

• Advisor: Jaegul Choo

• Ph.D in Grad. school of AI

Korea Advanced Institute of Science and Technology (KAIST)

2018.03 - 2020.02 

• Advisor: Jong C. Park

• M.S. in School of Computing

• Thesis: Generating Diverse Sentential Arguments on Controversial Topics with a Memory-augmented Generation Model

Korea Advanced Institute of Science and Technology (KAIST)

2013.03 - 2018.02 

• BS in School of Computing (major) Dept. of Chemistry (minor)