通过语义融合与知识对齐，提升神经符号推理的准确性与可解释性。
Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment
- 用上下文嵌入合并节点，减少冗余信息。
- 借助预训练分类器验证句子蕴含关系，提升边质量。
- 对接外部知识图谱，增强缺失上下文，适合开放域应用。
本报告扩展了谱神经符号推理（Spectral NSR）框架，引入三项语义基础增强：（1）使用上下文嵌入（如Sentence-BERT、SimCSE）的Transformer模型进行节点合并，降低冗余；（2）采用预训练自然语言推理分类器（如RoBERTa、DeBERTa）进行句级蕴含验证，提升边质量；（3）与外部知识图谱（如ConceptNet、Wikidata）对齐，补全缺失上下文。这些改进在ProofWriter、EntailmentBank和CLUTRR基准上实现一致准确率提升（最高+3.8%），增强对抗样本泛化能力，降低推理噪声。核心创新在于在谱推理前完成语义与符号优化，无需二次注意力机制，实现高效、可解释且可扩展的推理。结果是一个更鲁棒、可解释、适合真实场景部署的系统。
原文摘要 · Abstract (English)
This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements: (1) transformer-based node merging using contextual embeddings (e.g., Sentence-BERT, SimCSE) to reduce redundancy, (2) sentence-level entailment validation with pretrained NLI classifiers (e.g., RoBERTa, DeBERTa) to improve edge quality, and (3) alignment with external knowledge graphs (e.g., ConceptNet, Wikidata) to augment missing context. These modifications enhance graph fidelity while preserving the core spectral reasoning pipeline. Experimental results on ProofWriter, EntailmentBank, and CLUTRR benchmarks show consistent accuracy gains (up to +3.8\%), improved generalization to adversarial cases, and reduced inference noise. The novelty lies in performing semantic and symbolic refinement entirely upstream of the spectral inference stage, enabling efficient, interpretable, and scalable reasoning without relying on quadratic attention mechanisms. In summary, this work extends the Spectral NSR framework with modular, semantically grounded preprocessing steps that improve graph quality without altering the core spectral reasoning engine. The result is a more robust, interpretable, and scalable reasoning system suitable for deployment in open-domain and real-world settings.
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。