用符号推理让语言模型既准确又可解释，特别适合医疗金融场景。
CLMN: Concept based Language Models via Neural Symbolic Reasoning
- 概念用连续向量表示，结合模糊逻辑建模动态交互关系。
- 在多个数据集上比现有方法准确率更高，解释性更强。
- 适合需要透明决策的高风险领域，如医疗、金融分析。
深度学习推动了自然语言处理的发展，但在可解释性方面仍受限，尤其在医疗和金融领域。概念瓶颈模型在视觉领域通过人类可理解的概念关联预测结果，但现有的NLP版本要么使用二值激活破坏文本表征，要么依赖隐式概念削弱语义表达，且很少建模否定、上下文等动态概念交互。我们提出概念语言模型网络（CLMN），一种神经符号框架，在保持性能的同时提升可解释性。CLMN将概念表示为连续的、可读的嵌入，并采用模糊逻辑推理学习自适应的交互规则，明确描述概念如何相互影响及决定最终输出。模型在原始文本特征基础上融合概念感知表示，并自动推导出可解释的逻辑规则。在多个数据集和预训练语言模型上，CLMN在准确率上优于现有概念基方法，同时显著提升解释质量。结果表明，在统一概念空间中融合神经表示与符号推理，可实现实用且透明的自然语言系统。
原文摘要 · Abstract (English)
Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text representations or latent concepts that weaken semantics, and they rarely model dynamic concept interactions such as negation and context. We introduce the Concept Language Model Network (CLMN), a neural-symbolic framework that keeps both performance and interpretability. CLMN represents concepts as continuous, human-readable embeddings and applies fuzzy-logic reasoning to learn adaptive interaction rules that state how concepts affect each other and the final decision. The model augments original text features with concept-aware representations and automatically induces interpretable logic rules. Across multiple datasets and pre-trained language models, CLMN achieves higher accuracy than existing concept-based methods while improving explanation quality. These results show that integrating neural representations with symbolic reasoning in a unified concept space can yield practical, transparent NLP systems.
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。