activity
20242026
collaborators

5 papers

cs.CL2026

Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents

Minbyul Jeong

Web-agent benchmarks overwhelmingly measure depth -- pinning one obscure answer behind a chain of constraints -- while breadth, exhaustively enumerating a closed set and filling ea…

cs.AI2025

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training

Yein Park, Minbyul Jeong, Jaewoo Kang

The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (…

cs.AI2025

Trustworthy Agents for Electronic Health Records through Confidence Estimation

Yongwoo Song, Minbyul Jeong, Mujeen Sung

Large language models (LLMs) show promise for extracting information from Electronic Health Records (EHR) and supporting clinical decisions. However, deployment in clinical setting…

cs.CL2025

Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information

Yein Park, Chanwoong Yoon, Jungwoo Park +2

While the ability of language models to elicit facts has been widely investigated, how they handle temporally changing facts remains underexplored. We discover Temporal Heads, spec…

cs.CL2024

ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains

Yein Park, Chanwoong Yoon, Jungwoo Park +3

Large language models (LLMs) have brought significant changes to many aspects of our lives. However, assessing and ensuring their chronological knowledge remains challenging. Exist…