用大模型把机器学习解释变成自然语言故事，更易懂。
Explingo: Explaining AI Predictions using Large Language Models
- 用大模型将传统解释转为流畅的自然语言叙述
- 生成内容在准确、完整、通顺、简洁上得分高
- 适合需要可读解释的AI应用开发者
机器学习模型的解释对决策者至关重要。我们探索使用大语言模型（LLM）将传统解释（如SHAP）转化为符合自然交流习惯的可读叙事。针对两个核心问题：（1）大模型能否可靠生成高质量叙述？（2）如何有效评估叙述质量？我们提出Explingo，包含两个基于大模型的子系统：叙述生成器（Narrator）和评分器（Grader）。Narrator将机器学习解释转化为自然语言描述，Grader从准确性、完整性、流畅性和简洁性等维度打分。实验表明，大模型能生成高分叙述，尤其在少量人工标注与自举样本引导下表现优异。但复杂领域中的叙述评分仍具挑战。研究成果已集成至开源工具中，支持后续应用。
原文摘要 · Abstract (English)
Explanations of machine learning (ML) model predictions generated by Explainable AI (XAI) techniques such as SHAP are essential for people using ML outputs for decision-making. We explore the potential of Large Language Models (LLMs) to transform these explanations into human-readable, narrative formats that align with natural communication. We address two key research questions: (1) Can LLMs reliably transform traditional explanations into high-quality narratives? and (2) How can we effectively evaluate the quality of narrative explanations? To answer these questions, we introduce Explingo, which consists of two LLM-based subsystems, a Narrator and Grader. The Narrator takes in ML explanations and transforms them into natural-language descriptions. The Grader scores these narratives on a set of metrics including accuracy, completeness, fluency, and conciseness. Our experiments demonstrate that LLMs can generate high-quality narratives that achieve high scores across all metrics, particularly when guided by a small number of human-labeled and bootstrapped examples. We also identified areas that remain challenging, in particular for effectively scoring narratives in complex domains. The findings from this work have been integrated into an open-source tool that makes narrative explanations available for further applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。