大型语言模型（LLMs）能否进行反事实自我解释？
Can LLMs Explain Themselves Counterfactually?
AI总结：
本研究针对LLMs的自我生成反事实解释（SCEs）展开测试，发现LLMs在生成SCEs时存在困难，且生成SCEs时其预测常与自身反事实推理不一致。
摘要：
解释是深入了解机器学习模型行为、校准用户信任及确保合规性的重要工具。过去几年涌现出大量事后解释生成方法，其中许多涉及计算模型梯度或求解专门设计的优化问题。然而，得益于大型语言模型（LLMs）卓越的推理能力，自我解释（即通过提示让模型解释其输出）已成为新范式。本研究聚焦自我生成反事实解释（SCEs）这一特定类型的自我解释，设计测试以衡量LLMs生成SCEs的效果。对不同LLM家族、模型规模、温度设置及数据集的分析表明，LLMs有时难以生成SCEs；即便生成，其预测也常与自身反事实推理不一致。
英文摘要：
Explanations are an important tool for gaining insights into the behavior of ML models, calibrating user trust and ensuring regulatory compliance. Past few years have seen a flurry of post-hoc methods for generating model explanations, many of which involve computing model gradients or solving specially designed optimization problems. However, owing to the remarkable reasoning abilities of Large Language Model (LLMs), self-explanation, that is, prompting the model to explain its outputs has recently emerged as a new paradigm. In this work, we study a specific type of self-explanations, self-generated counterfactual explanations (SCEs). We design tests for measuring the efficacy of LLMs in generating SCEs. Analysis over various LLM families, model sizes, temperature settings, and datasets reveals that LLMs sometimes struggle to generate SCEs. Even when they do, their prediction often does not agree with their own counterfactual reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
