Junseok Kim

junseokkim00

·

https://junseokkim00.github.io/

AI & ML interests

Interpretability

Recent Activity

authored a paper 1 day ago

Personalized Privacy Control in LLMs via Attention Head Intervention

authored a paper 1 day ago

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning

authored a paper 1 day ago

Persona is a Double-edged Sword: Enhancing the Zero-shot Reasoning by Ensembling the Role-playing and Neutral Prompts

View all activity

Organizations

junseokkim00 's papers 3

arxiv:2608.21209

arxiv:2601.02970

arxiv:2408.08631