Two papers accepted to Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2026
Embedded Files
Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Utility under Harmful Finetuning Attacks
Seokil Ham, Yubin Choi, Yujin Yang, Younghun Kim, Seungju Cho and Changick Kim
Generalizable Prompt Tuning for Audio-Language Models via Semantic Expansion
Jaehyuk Jang*, Wonjun Lee*, Kangwook Ko* and Changick Kim (* These three authors contributed equally)
Page updated
Google Sites
Report abuse