ReCBM：面向概念瓶颈模型的不确定性门控关系推理框架
ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models
浏览论文内容
中文总结 AI 辅助
本文针对概念瓶颈模型（CBMs）在不可靠概念状态下鲁棒推理不足的问题，提出ReCBM框架，引入语义概念关系并以不确定性调节概念贡献，在多数据集实验中验证了其在概念异常场景下的性能与紧凑概念子集提取能力。
中文摘要 AI 辅助
概念瓶颈模型（Concept Bottleneck Models, CBMs）通过将预测建立在人类可理解的概念之上，提供了一种可解释的框架，支持语义检查和测试时干预。近期的变体通过更丰富的概念表示、不确定性估计和依赖建模改进了CBMs，但针对不可靠概念状态的鲁棒推理仍未得到充分探索。若缺乏此类推理，误导性的语义证据会通过瓶颈传播，损害解释性和下游预测。为解决该问题，本文提出ReCBM——一种面向CBMs的不确定性门控关系推理框架。ReCBM将语义定义的概念关系引入瓶颈，并利用不确定性指导其优化；通过建模共现、蕴含和排斥关系，ReCBM明确了概念间的证据交换方式，同时不确定性会调节每个概念在此过程中的贡献。在多个不同数据集上的实验表明，ReCBM在概念缺失和翻转的情况下提升了概念与任务的恢复能力，支持不确定性感知的干预，且在不降低下游性能的前提下提取出了紧凑的任务相关概念子集。
英文摘要
Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time intervention. Recent variants have improved CBMs through richer concept representations, uncertainty estimation, and dependency modeling. However, robust reasoning under unreliable concept states remains underexplored. Without such reasoning, misleading semantic evidence can propagate through the bottleneck, compromising both explanations and downstream predictions. To address this issue, we propose ReCBM, an uncertainty-gated relational reasoning framework for CBMs. ReCBM introduces semantically defined concept relations into the bottleneck and uses uncertainty to guide their refinement. By modeling co-occurrence, implication, and exclusion, ReCBM specifies how evidence is exchanged across concepts, while uncertainty modulates the contribution of each concept during this process. Experiments across diverse datasets showed that ReCBM improved concept and task recovery under missing and flipped concepts, supported uncertainty-aware intervention, and extracted compact task-relevant concept subsets without degrading downstream performance.
