用于评估黑盒LLM忠实性的局部解释与自解释
Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
AI总结：
本文提出利用局部扰动和受留一法启发的自解释技术，识别LLM生成正确答案的关键部分，并引入新指标将其与模型自解释对比以评估忠实性，在Natural Questions数据集上验证了方法的有效性。
摘要：
本文引入了一项新任务，利用局部扰动和自解释来评估大型语言模型（LLMs）的忠实性。许多LLM通常需要额外上下文才能正确回答某些问题。为此，我们提出了一种新的高效可解释性替代技术，其灵感源自常用的留一法。利用该方法，我们识别出LLM生成正确答案所需的充分且必要部分，以此作为解释。我们提出了一种评估忠实性的指标，将这些关键部分与模型的自解释进行比较。我们使用Natural Questions数据集验证了该方法，证明了其在解释模型决策和评估忠实性方面的有效性。
英文摘要：
This paper introduces a novel task to assess the faithfulness of large language models (LLMs) using local perturbations and self-explanations. Many LLMs often require additional context to answer certain questions correctly. For this purpose, we propose a new efficient alternative explainability technique, inspired by the commonly used leave-one-out approach. Using this approach, we identify the sufficient and necessary parts for the LLM to generate correct answers, serving as explanations. We propose a metric for assessing faithfulness that compares these crucial parts with the self-explanations of the model. Using the Natural Questions dataset, we validate our approach, demonstrating its effectiveness in explaining model decisions and assessing faithfulness.
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。
