1
From Plausible to Actionable: A Position on LLM Self-Explanations
LLM自我解释从“看似合理”到“切实可用”的转变，探讨如何让模型解释更具实用价值，为可解释性研究提供新方向。
arXiv:2607.15957v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate natural language explanations that rationalize their own dec…