基于概念的解释的可读性与忠实性评估
Evaluating Readability and Faithfulness of Concept-based Explanations
AI总结：
针对基于概念的大语言模型解释缺乏统一评估框架的问题，提出概念形式化定义，通过扰动量化忠实性、用自动确定性指标衡量可读性，并基于测量理论设计可推广的元评估方法，经实验为指标选择提供依据。
摘要：
随着通用大语言模型（Large Language Models, LLMs）日益普及，人们需要对模型行为提供更具全局性的解释。基于概念的解释作为解释大语言模型所习得高层模式的一种有前景的方向应运而生。然而这类解释的评估面临独特挑战，尤其是因其非局部特性以及在模型隐藏空间中的高维表示。现有方法从不同视角研究概念，缺乏统一的形式化定义，这使得评估概念的核心指标——即忠实性与可读性——颇具难度。为填补这一空白，我们提出了一个适用于多种基于概念的解释场景的概念形式化定义。在此基础上，我们通过扰动来量化概念解释的忠实性，并通过一个优化问题确保在高维空间中对不同概念施加充分的扰动。可读性则通过一种自动且确定性的指标来近似，该指标准确量化能最大程度激活某个概念、同时符合人类理解的模式的连贯性。最后，我们基于测量理论应用了一种元评估方法来评估这些指标，该方法同样可推广至其他类型的解释或任务。我们开展了广泛的实验分析，为解释评估指标的选择提供参考依据。
英文摘要：
With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by LLMs. Yet their evaluation poses unique challenges, especially due to their non-local nature and high dimensional representation in a model's hidden space. Current methods approach concepts from different perspectives, lacking a unified formalization. This makes evaluating the core measures of concepts, namely faithfulness or readability, challenging. To bridge the gap, we introduce a formal definition of concepts generalizing to diverse concept-based explanations' settings. Based on this, we quantify the faithfulness of a concept explanation via perturbation. We ensure adequate perturbation in the high-dimensional space for different concepts via an optimization problem. Readability is approximated via an automatic and deterministic measure, quantifying the coherence of patterns that maximally activate a concept while aligning with human understanding. Finally, based on measurement theory, we apply a meta-evaluation method for evaluating these measures, generalizable to other types of explanations or tasks as well. Extensive experimental analysis has been conducted to inform the selection of explanation evaluation measures.
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。
