1
Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs
提出多Token归因方法，让长推理链LLM的可解释性更高效、更忠实，ICML Spotlight论文。
arXiv:2602.01914v2 Announce Type: replace Abstract: Token attribution methods provide intuitive explanations for language model outputs by identifying…