2 papers
cs.CL2026
A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals
Yuri Son, Seunghee Kim, Hyuhng Joon Kim +1
Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate safety policies (safety-based re…
cs.CL2025
Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
Yejin Yoon, Yuri Son, Namyoung So +5
Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world c…