We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more broadly applicable training objective for abductive reasoning, resulting in better interpretability and higher accuracy when solving Raven's progressive matrices (RPM). ARLC allows both programming domain knowledge and learning the rules underlying a data distribution. We evaluate ARLC on the I-RAVEN dataset, showcasing state-of-the-art accuracy across both in-distribution and out-of-distribution (unseen attribute-rule pairs) tests. ARLC surpasses neuro-symbolic and connectionist baselines, including large language models, despite having orders of magnitude fewer parameters. We show ARLC's robustness to post-programming training by incrementally learning from examples on top of programmed knowledge, which only improves its performance and does not result in catastrophic forgetting of the programmed solution. We validate ARLC's seamless transfer learning from a 2x2 RPM constellation to unseen constellations. Our code is available at https://github.com/IBM/abductive-rule-learner-with-context-awareness.
SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China(认知与决策智能复杂系统重点实验室,自动化研究所,中国科学院,北京,中国);School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China(人工智能学院,中国科学院大学,北京,中国)
From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development
The Chinese University of Hong Kong, Sha Tin, NT, Hong Kong(香港中文大学);Université de Montréal, Montréal, Quebéc, Canada(蒙特利尔大学);McGill University, Montréal, Quebéc, Canada(麦吉尔大学);Mila - Quebéc AI Institute, Montréal, Quebéc, Canada(魁北克AI研究院);Huawei Noah’s Ark Lab, Montréal, Quebéc, Canada(华为诺亚实验室)
ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT
Northwestern Polytechnical University(西北工业大学);The University of Georgia(佐治亚大学);University of Electronic Science and Technology of China(电子科技大学);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);The University of Texas at Arlington(德克萨斯大学阿灵顿分校);ShanghaiTech University(上海科技大学);Shanghai United Imaging Intelligence Co., Ltd.(上海联影智能医疗科技有限公司)
Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection
National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室);School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院)
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
Allen Institute for Artificial Intelligence(艾伦人工智能研究所);Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);Stanford University(斯坦福大学)
One-Step Abductive Multi-Target Learning with Diverse Noisy Samples and Its Application to Tumour Segmentation for Breast Cancer
Institute of Clinical Pathology, West China Hospital, Sichuan University(四川大学华西医院临床病理研究所);ZHONG JIU Flash Medical Technology Co., Ltd.(中玖闪光医疗科技有限公司);Department of Pathology, West China Hospital, Sichuan University(四川大学华西医院病理科);Department of Civil Engineering, McGill University(麦吉尔大学土木工程系)
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
MARS 4.0 Fellowship, Cambridge AI Safety Hub(CAISH), University of Cambridge(MARS 4.0 Fellow,剑桥人工智能安全中心(CAISH),剑桥大学);AWS Generative AI Innovation Center, Amazon Web Services, USA(亚马逊生成AI创新中心,亚马逊网络服务,美国);Google, USA(谷歌,美国);Stanford University(斯坦福大学);Northeastern University, Seattle, WA, USA(东北大学,西雅图,华盛顿州,美国)
Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning
The Hong Kong Polytechnic University(香港理工大学);Hong Kong University(香港大学);South China University of Technology(华南理工大学);University of Toronto(多伦多大学);Peking Union Medical College Hospital(北京地坛医院);West China Hospital, Sichuan University(四川大学华西医院)
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
Fudan University(复旦大学);MMLab, The Chinese University of Hong Kong(中大香港人工智能实验室);Shanghai AI Laboratory(上海人工智能实验室);University of Science and Technology of China(中国科学技术大学);Nanjing University(南京大学)
Investigating Advanced Reasoning of Large Language Models via Black-Box Interaction
College of Artificial Intelligence, Nanjing University of Aeronautics(人工智能学院,南京航空航天大学);School of Electronics Engineering(电子工程学院);Computer Science, Peking University(计算机科学,北京大学);Theta Health Inc.(Theta健康公司)
Variable Binding for Sparse Distributed Representations: Theory and Applications
Neuromorphic Computing Lab, Intel Labs(英特尔实验室神经形态计算实验室);Redwood Center for Theoretical Neuroscience at the University of California, Berkeley(加州大学伯克利分校红杉理论神经科学中心);Intelligent systems Lab at Research Institutes of Sweden(瑞典研究院智能系统实验室)
符号推理和神经网络通常被认为是不兼容的方法。被称为向量符号架构(VSAs)的连接主义模型可能会弥合这一差距。然而,经典的VSA和神经网络仍然被认为是不兼容的。VSA通过密集的伪随机向量对符号进行编码,其中信息分布在整个神经元群体中。神经网络对特征进行局部编码,通常形成神经激活的稀疏向量。继Rachkovskij(2001); Laiho et al.(2015)之后,我们探索了具有稀疏分布表示的符号推理。VSA中的核心操作是向量之间的二元操作,以表达变量绑定和集合的表示。因此,代数操作使得VSA能够在固定维度的向量空间中表示和处理数据结构。使用压缩感知技术,我们首先表明,在VSAs密集向量之间的变量绑定在数学上等价于稀疏向量之间的张量积绑定,增加维数的操作。这个结果意味着一般稀疏向量的维保持绑定必须包括将张量矩阵减少到单个稀疏向量。研究了保持稀疏性的变量绑定的两种选择。一般稀疏向量的一种绑定方法扩展了早期的建议,将张量积减少到一个向量中,例如循环卷积。另一种方法仅针对稀疏分组码,即块循环卷积定义。我们的实验表明,变量绑定块码具有理想的属性,而绑定一般稀疏向量也工作,但有损,类似于以前的建议。我们展示了一个VSA与稀疏块码的示例应用程序,认知推理和分类,并讨论其相关的神经科学和神经网络。