conftrace_
← Authors

SungUk Shin

2 papers · 2025–2026 · 2 conferences · across top CS/AI conferences

Conferences

ACL (1) ICLR (1)

Top co-authors

Sungwon Park (1) Meeyoung Cha (1) Fangzhao Wu (1) Byung-Jun Lee (1) Youngjoon Kim (1)

Keywords

model alignment (1) malicious fine-tuning (1) large language model (1) safety guidance trigger (1) safety region (1)

Papers

SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger ACL 2026 Enhancing Graph Of Thought: Enhancing Prompts with LLM Rationales and Dynamic Temperature Control ICLR 2025