无需人工标注，自动构建完整概念体系提升文本分类可解释性
Towards Achieving Concept Completeness for Textual Concept Bottleneck Models
- 用小语言模型无监督生成概念标签，自动补全关键概念
- 在概念完备性和检测准确率上显著优于现有方法
- 适合需要高可解释性的NLP应用，如医疗、金融决策
文本概念瓶颈模型（TCBMs）是为文本分类设计的可解释模型，先预测一组关键概念再进行最终分类。本文提出完全文本概念瓶颈模型（CT-CBM），一种新型TCBM生成器，利用小型语言模型在无监督条件下生成概念标签，无需预先定义的人工标注概念或大模型标注。CT-CBM通过迭代识别并添加瓶颈层中重要且可辨识的概念，逐步构建完整的概念基础。在概念基础完备性和概念检测准确率方面，CT-CBM显著优于对比方法，为可靠提升NLP分类器的可解释性提供了一种有前景的解决方案。
原文摘要 · Abstract (English)
Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This paper proposes Complete Textual Concept Bottleneck Model (CT-CBM), a novel TCBM generator building concept labels in a fully unsupervised manner using a small language model, eliminating both the need for predefined human labeled concepts and LLM annotations. CT-CBM iteratively targets and adds important and identifiable concepts in the bottleneck layer to create a complete concept basis. CT-CBM achieves striking results against competitors in terms of concept basis completeness and concept detection accuracy, offering a promising solution to reliably enhance interpretability of NLP classifiers.
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。