评估黑箱模型解释方法的可靠性的开源框架
xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
- 构建统一评估框架，支持多种解释方法
- 覆盖图像与表格数据，涵盖多类评估指标
- 适合关注模型可解释性的研究者与开发者
机器学习与深度学习模型日益复杂，导致对透明性要求更高的高风险应用中，其决策过程难以理解。尽管后处理解释方法被广泛使用，但缺乏严谨评估，影响其可信度。xai_evals 是一个 Python 开源库，提供针对表格与图像数据的完整解释方法生成、基准测试与评估框架。集成 SHAP、LIME、Grad-CAM、Integrated Gradients（IG）和 Backtrace 等常用方法，并支持忠实性、敏感性与鲁棒性等评估指标。该工具提升模型可解释性，增强对 AI 系统的信任。项目已开源，地址为 https://pypi.org/project/xai-evals/。
原文摘要 · Abstract (English)
The growing complexity of machine learning and deep learning models has led to an increased reliance on opaque "black box" systems, making it difficult to understand the rationale behind predictions. This lack of transparency is particularly challenging in high-stakes applications where interpretability is as important as accuracy. Post-hoc explanation methods are commonly used to interpret these models, but they are seldom rigorously evaluated, raising concerns about their reliability. The Python package xai_evals addresses this by providing a comprehensive framework for generating, benchmarking, and evaluating explanation methods across both tabular and image data modalities. It integrates popular techniques like SHAP, LIME, Grad-CAM, Integrated Gradients (IG), and Backtrace, while supporting evaluation metrics such as faithfulness, sensitivity, and robustness. xai_evals enhances the interpretability of machine learning models, fostering transparency and trust in AI systems. The library is open-sourced at https://pypi.org/project/xai-evals/ .
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。