迈向忠实性的必要一步：测量与提升自由文本解释的一致性
A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations
AI总结：
本文扩展证据权重提出 PEX 一致性度量，发现大模型超 62% 的自由文本解释缺乏该一致性，并通过直接偏好优化在三个模型系列上将其提升 43.1%–292.3%，且忠实性最高提升 9.7%。
摘要：
忠实的自由文本解释对于确保高风险 AI 决策情境中的透明度至关重要，但语言模型难以生成这类解释，人类也难以对其进行评估。本文中，我们通过扩展证据权重（weight of evidence）概念，提出了一种用于预测—解释（Prediction-EXplanation，PEX）一致性的度量。该度量量化自由文本解释对某项预测的支持或反对程度，是解释忠实性的一个重要方面。我们的分析显示，大型语言模型生成的解释中有超过 62% 缺乏这种一致性。我们表明，应用直接偏好优化（direct preference optimization）可在三个模型系列中提升所生成解释的一致性，提升幅度从 43.1% 到 292.3% 不等。此外，我们证明，优化该一致性度量最多可将解释忠实性提升 9.7%。
英文摘要：
Faithful free-text explanations are important to ensure transparency in high-stakes AI decision-making contexts, but they are challenging to generate by language models and assess by humans. In this paper, we present a measure for Prediction-EXplanation (PEX) consistency, by extending the concept of weight of evidence. This measure quantifies how much a free-text explanation supports or opposes a prediction, serving as an important aspect of explanation faithfulness. Our analysis reveals that more than 62% explanations generated by large language models lack this consistency. We show that applying direct preference optimization improves the consistency of generated explanations across three model families, with improvement ranging from 43.1% to 292.3%. Furthermore, we demonstrate that optimizing this consistency measure can improve explanation faithfulness by up to 9.7%.
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。
