作者位次 #3/4ACL 2026Findings· Findings of ACL
Aligning What LLM s Do and Say: Towards Self-Consistent Explanations
Sahar Admoni · Ofra Amir · Assaf Hallak · Yftah Ziser
摘要
Large language models (LLMs) seem to offer an easy path to interpretability: just ask them to explain their answers. Yet the features driving an answer often differ from those emphasized in its explanation, meaning post-hoc rationales can misrepresent what actually shaped the model’s output. We q...