Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations
School of Computer Science, University of Waterloo, Waterloo, Canada(计算机科学学院,滑铁卢大学,滑铁卢,加拿大);Centre for Theoretical Neuroscience, University of Waterloo(理论神经科学中心,滑铁卢大学)
Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly those that require precise rule following, as often found in mathematical reasoning. This paper introduces a novel neurosymbolic method that improves LLM reasoning by encoding hidden states into neurosymbolic vectors, enabling problem-solving within a neurosymbolic vector space. The results are decoded and merged with the original hidden state, significantly boosting the model's performance on numerical reasoning tasks. By offloading computation through neurosymbolic representations, this method enhances efficiency, reliability, and interpretability. Experimental results demonstrate an average of 88.6% lower cross-entropy loss and 15.4 times more problems correctly solved on a suite of mathematical reasoning tasks compared to chain-of-thought prompting and supervised fine-tuning (LoRA), without degrading performance on other tasks. We make our code available at: https://github.com/vdhanraj/Neurosymbolic-LLM.
The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning
Politecnico di Milano(米兰理工大学);ELLIS Institute Finland(芬兰ELLIS研究所);Åbo Akademi University(奥博 Akademi 大学);Samsung AI(三星人工智能研究院);Delft University of Technology(代尔夫特理工大学);Stony Brook University(石溪大学);Politecnico di Torino(都灵理工大学);University of Stuttgart(斯图加特大学);Graz University of Technology(格拉茨工业大学);Lockheed Martin, Advanced Technology Labs(洛克希德·马丁公司先进技术实验室);BrainCreators(BrainCreators公司);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);University of Amsterdam(阿姆斯特丹大学);University of Edinburgh(爱丁堡大学);UCLA(加利福尼亚大学洛杉矶分校)
Department of Computer Science and Leuven.AI, KU Leuven, Belgium(1 计算机科学系和 Leuven.AI,KU Leuven,比利时);Centre for Applied Autonomous Sensor Systems (AASS), Örebro University, Sweden(3 应用自主传感器系统中心(AASS),Örebro大学,瑞典)
Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition
Department of ECSE, Faculty of Engineering, Monash University, Australia(莫纳什大学工程学院电子与计算机工程系,澳大利亚);AIM for Health Lab, Faculty of Information Technology, Monash University, Australia(莫纳什大学信息科技学院健康人工智能实验室,澳大利亚);Department of DSAI, Faculty of Information Technology, Monash University, Australia(莫纳什大学信息科技学院数据科学与人工智能系,澳大利亚)
Towards Unified Neurosymbolic Reasoning on Knowledge Graphs
Saw Swee Hock School of Public Health, National University of Singapore(新加坡国立大学 Saw Swee Hock 公共卫生学院);School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院);State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所多模态人工智能系统国家重点实验室);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院)
本文提出统一神经符号推理框架 Tunsr,通过一致推理图结构、前向逻辑消息传递和 FARI 规则归纳算法,在 19 个数据集上有效融合神经与符号推理并覆盖多种知识图谱推理场景。
Neurosymbolic AI for Travel Demand Prediction: Integrating Decision Tree Rules into Neural Networks
Department of Information Systems University of Maryland Baltimore County Baltimore, MD, US(信息系统系马里兰大学巴尔的摩县);Department of Mechanical Engineering Baylor University Waco,TX, US(机械工程系贝勒大学)
SCALAR: A Neurosymbolic Framework for Automated Conjecture and Reasoning in Quantum Circuit Analysis
1Department of Computer Science, Texas A\&M University, College Station, USA;2NVIDIA Corporation, Santa Clara, USA;Artificial Intelligence Division (CAI-3), Los Alamos National Laboratory, Los Alamos, USA
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)
Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
Golden Gate University, San Francisco Foundation(金门大学,旧金山基金会);AgenticOS (FAOS)(AgenticOS(FAOS));Associate Director, Data, Digital & IT Novartis Healthcare Pvt. Ltd.(数据、数字与IT部门,诺华健康有限公司);Novartis Healthcare Pvt. Ltd., Hyderabad, India(诺华健康有限公司,海得拉巴,印度)