本文提出了sandra，一个结合向量表示与演绎推理的神经符号推理器。Sandra构建了一个受本体约束的向量空间，并在其上进行推理。该推理器的几何特性使其能够与神经网络结合，弥合了与符号知识表示之间的差距。Sandra基于Description and Situation (DnS)本体设计模式，即框架语义学的一种形式化。给定一组事实（一个情境），它允许推断所有可能的视角（描述），从而为其提供合理的解释，即使在不完整信息存在的情况下也是如此。我们证明了我们的方法在DnS模型下是正确的。我们在两个不同任务及其标准基准上进行了实验，证明在不增加复杂性的情况下，sandra (i) 优于所有基线，(ii) 在分类过程中提供可解释性，以及 (iii) 允许对先验设计的向量空间进行控制。
英文摘要：
This paper presents sandra, a neuro-symbolic reasoner combining vectorial representations with deductive reasoning. Sandra builds a vector space constrained by an ontology and performs reasoning over it. The geometric nature of the reasoner allows its combination with neural networks, bridging the gap with symbolic knowledge representations. Sandra is based on the Description and Situation (DnS) ontology design pattern, a formalization of frame semantics. Given a set of facts (a situation) it allows to infer all possible perspectives (descriptions) that can provide a plausible interpretation for it, even in presence of incomplete information. We prove that our method is correct with respect to the DnS model. We experiment with two different tasks and their standard benchmarks, demonstrating that, without increasing complexity, sandra (i) outperforms all the baselines (ii) provides interpretability in the classification process, and (iii) allows control over the vector space, which is designed a priori.
Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning
Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Academy of Artificial Intelligence for Science（上海人工智能科学研究院）；INFTECH；University of Waterloo（滑铁卢大学）
Explainable Moral Values: a neuro-symbolic approach to value classification
University of Pisa（比萨大学）；National Research Council（国家研究委员会）；University of Bologna（博洛尼亚大学）；Peoples' Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学（RUDN大学））；Joint Institute for Nuclear Research（联合核子研究所）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；University of Skövde（舍夫德大学）
Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
Chinese Institute for Brain Research, Beijing（北京脑科学与类脑研究中心）；Beijing Key Laboratory of Brain Science and Brain-Machine Interface（北京脑科学与脑机接口重点实验室）；Sun Yat-sen University（中山大学）
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
Beijing Institute of Technology（北京理工大学）；Zhongguancun Academy（中关村学院）；Xinjiang Future Enterprise Incubator Co., Ltd.（新疆未来企业孵化器有限公司）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations
University of Amsterdam（阿姆斯特丹大学）；University of Southern California（南加州大学）；Rensselaer Polytechnic Institute（拉特格斯理工学院）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
Structure-Internalized Rule Language Model for Faithful Knowledge Graph Reasoning
Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology)（大数据知识工程重点实验室（合肥工业大学））；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息学院）；Nanjing University of Science and Technology（南京理工大学）
Evaluating GPT-5 as a Multimodal Clinical Reasoner: A Landscape Commentary
Department of Radiation Oncology, Winship Cancer Institute, Emory University School of Medicine（放射肿瘤科，Winship癌症研究所，埃默里大学医学院）；Department of Biomedical Engineering, Georgia Institute of Technology（生物医学工程系，佐治亚理工学院）
