Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang. Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 4806-4844, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.