Ziwen Pan, Zihan Liang 0002, Jad Kabbara, Ali Emami. DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 4940-4980, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.