Junyuan Hong
Junyuan Hong
Publications
Experiences
Teaching
CoSTA@NUS Lab
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
Minh Khoi Ho
,
Zihao Zhu
,
Runchuan Zhu
,
Levina Li
,
Zhiwen Fan
,
Zhangyang Wang
,
Junyuan "Jason" Hong
July 2026
Type
Conference paper
Publication
In
the 3rd Conference on Language Modeling (COLM)
LLM
Safety
Cognition
Junyuan "Jason" Hong
Assistant Professor
My research interest lies in the interaction of responsible AI and healthcare.
Related
CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
Extracting and Understanding the Superficial Knowledge in Alignment
HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning
The Last Human-Written Paper: Agent-Native Research Artifacts
Cite
×