1
Faithfulness Evaluation for Decoder-only LLM Attributions with Controlled Retained Information
提出控制保留信息的新方法，可靠评估Decoder-only LLM的归因忠实度，为可解释性研究提供关键视角。
arXiv:2601.03089v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly evaluated with input attribution methods, yet …