用智能代理动态调整概念数量，让图像分类更准且可解释。
Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models
- 用LLM代理动态优化概念数量，避免冗余或覆盖不足。
- 在6个数据集上提升分类准确率6%，可解释性评估提升30%。
- 新模型支持人工修正概念评分，更贴合人类认知逻辑。
概念瓶颈模型（CBMs）将图像分类分解为由可解释、人类可读概念驱动的过程。近期研究利用大语言模型（LLMs）生成候选概念，但一个关键问题仍存：应使用多少概念才最优？当前概念库存在冗余或覆盖不足的问题。为此，我们提出一种基于代理的动态方法，根据环境反馈调整概念库，优化概念数量以实现充分而简洁的覆盖。此外，我们提出条件概念瓶颈模型（CoCoBMs），克服传统CBMs在概念评分机制上的局限。该模型提升了对每个概念在分类任务中贡献度的评估精度，并引入可编辑矩阵，使LLM能修正与内部知识冲突的概念评分。在6个数据集上的评估显示，该方法不仅使分类准确率提升6%，还使可解释性评估提升30%。
原文摘要 · Abstract (English)
Concept Bottleneck Models (CBMs) decompose image classification into a process governed by interpretable, human-readable concepts. Recent advances in CBMs have used Large Language Models (LLMs) to generate candidate concepts. However, a critical question remains: What is the optimal number of concepts to use? Current concept banks suffer from redundancy or insufficient coverage. To address this issue, we introduce a dynamic, agent-based approach that adjusts the concept bank in response to environmental feedback, optimizing the number of concepts for sufficiency yet concise coverage. Moreover, we propose Conditional Concept Bottleneck Models (CoCoBMs) to overcome the limitations in traditional CBMs' concept scoring mechanisms. It enhances the accuracy of assessing each concept's contribution to classification tasks and feature an editable matrix that allows LLMs to correct concept scores that conflict with their internal knowledge. Our evaluations across 6 datasets show that our method not only improves classification accuracy by 6% but also enhances interpretability assessments by 30%.
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。