从提示大型语言模型得到的推理解释的可解释性如何？
How Interpretable are Reasoning Explanations from Prompting Large Language Models?
AI总结：
本文从忠实性、鲁棒性和实用性三个维度系统评估了多种提示技术下思维链推理的可解释性，并提出自蕴含对齐思维链方法，使可解释性提升超过70%。
摘要：
提示工程因能在众多任务中提升大型语言模型的性能而受到广泛关注。诸如思维链（Chain-of-Thought）等技术不仅能提高任务表现，还能勾勒出清晰的推理步骤轨迹，为受众提供一种具体可见的解释形式。此前关于可解释性的研究仅沿单一维度——即忠实性——来评估思维链产生的推理链。我们提出了一种全面且多层面的可解释性评估方法，在多个常识推理基准上不仅考察忠实性，还考察鲁棒性和实用性。同样，我们的研究并不局限于单一提示技术，而是广泛覆盖大型语言模型中使用的多种主流提示技术，从而确保评估范围广泛且详尽。此外，我们引入了一种简单的可解释性对齐技术，称为自蕴含对齐思维链（Self-Entailment-Alignment Chain-of-thought），该技术在可解释性的多个维度上带来了超过70%的提升。代码可在 https://github.com/SenticNet/CoT_interpretability 获取。
英文摘要：
Prompt Engineering has garnered significant attention for enhancing the performance of large language models across a multitude of tasks. Techniques such as the Chain-of-Thought not only bolster task performance but also delineate a clear trajectory of reasoning steps, offering a tangible form of explanation for the audience. Prior works on interpretability assess the reasoning chains yielded by Chain-of-Thought solely along a singular axis, namely faithfulness. We present a comprehensive and multifaceted evaluation of interpretability, examining not only faithfulness but also robustness and utility across multiple commonsense reasoning benchmarks. Likewise, our investigation is not confined to a single prompting technique; it expansively covers a multitude of prevalent prompting techniques employed in large language models, thereby ensuring a wide-ranging and exhaustive evaluation. In addition, we introduce a simple interpretability alignment technique, termed Self-Entailment-Alignment Chain-of-thought, that yields more than 70\% improvements across multiple dimensions of interpretability. Code is available at https://github.com/SenticNet/CoT_interpretability
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。
