1
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
研究发现LLM给出的解释并不反映其真实推理过程，提出基于模型自身输入信念评估解释充分性的新方法。
arXiv:2606.28615v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explana…