用反事实推理提升大模型识别分类关键词的能力
Does Using Counterfactual Help LLMs Explain Textual Importance in Classification?
- 通过反事实推理分析关键词对分类的影响
- 反事实方法显著提升了关键词识别准确率
- 适合需要可解释性的大模型应用开发
大语言模型（LLMs）因海量训练数据和庞大参数量，在多个领域展现出强大能力，尤其在文本分类任务中表现优异，这促使人们关注其决策过程的可解释性。由于实际应用中存在模型黑箱化和调用成本高的限制，本文研究将反事实推理融入大模型推理过程，如何影响其识别导致分类决策的关键词汇的能力。为此，提出一种称为‘决策变化率’的量化框架，用于衡量关键词汇的重要性。实验结果表明，引入反事实机制有助于更有效地识别出对分类贡献最大的词语。
原文摘要 · Abstract (English)
Large language models (LLMs) are becoming useful in many domains due to their impressive abilities that arise from large training datasets and large model sizes. More recently, they have been shown to be very effective in textual classification tasks, motivating the need to explain the LLMs' decisions. Motivated by practical constrains where LLMs are black-boxed and LLM calls are expensive, we study how incorporating counterfactuals into LLM reasoning can affect the LLM's ability to identify the top words that have contributed to its classification decision. To this end, we introduce a framework called the decision changing rate that helps us quantify the importance of the top words in classification. Our experimental results show that using counterfactuals can be helpful.
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。