文本分类器反事实解释方法的比较分析
A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers
AI总结:
本文比较了五种为BERT文本分类器生成反事实解释的方法,发现白盒替换方法有效但欠自然,LLM方法自然但常无效,建议结合两者优势开发新方法。
摘要:
反事实解释可用于解释和调试文本分类器,通过生成最小化改变的文本输入来改变分类器的输出。在本工作中,我们使用三个评估指标,在两个数据集上评估了五种为BERT文本分类器生成反事实解释的方法。实验结果表明,成熟的基于替换的白盒方法在生成有效的、能改变分类器输出的反事实方面表现良好。相比之下,基于大型语言模型(LLM)的新方法擅长生成自然且语言上合理的文本反事实,但往往无法生成能改变分类器输出的有效反事实。基于这些结果,我们建议开发新的反事实解释方法,结合成熟的基于梯度的方法和较新的基于LLM的技术的优势,以生成高质量、有效且合理的文本反事实解释。
英文摘要:
Counterfactual explanations can be used to interpret and debug text classifiers by producing minimally altered text inputs that change a classifier's output. In this work, we evaluate five methods for generating counterfactual explanations for a BERT text classifier on two datasets using three evaluation metrics. The results of our experiments suggest that established white-box substitution-based methods are effective at generating valid counterfactuals that change the classifier's output. In contrast, newer methods based on large language models (LLMs) excel at producing natural and linguistically plausible text counterfactuals but often fail to generate valid counterfactuals that alter the classifier's output. Based on these results, we recommend developing new counterfactual explanation methods that combine the strengths of established gradient-based approaches and newer LLM-based techniques to generate high-quality, valid, and plausible text counterfactual explanations.
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。