arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Oxford(牛津大学)

2026-01-13 至 2026-01-13 共收录 4
2508.08344 2026-01-13 cs.AI

What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge

什么破坏了基于知识图谱的RAG?对在不完整知识下推理的基准测试和经验洞察

Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Steffen Staab, Evgeny Kharlamov

机构 * University of Oslo(奥斯陆大学) Bosch Center for AI(博世人工智能中心) University of Stuttgart(斯图加特大学) Amazon(亚马逊公司) University of Oxford(牛津大学) The University of Manchester(曼彻斯特大学) University of Southampton(南安普顿大学)

AI总结 本文提出BRINK基准测试,揭示了当前KG-RAG方法在知识不完整时推理能力有限,依赖内部记忆且泛化能力各异。

Comments Accepted as a main conference paper at EACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.13772 2026-01-13 cs.SD cs.AI cs.LG cs.MM eess.AS

Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models

Jailbreak-AudioBench: 对大型音频语言模型中 jailbreak 威胁的深入评估与分析

Hao Cheng, Erjia Xiao, Jing Shao, Yichi Wang, Le Yang, Chao Shen, Philip Torr, Jindong Gu, Renjing Xu

机构 * Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) University of Oxford(牛津大学) Xi’an Jiaotong University(西安交通大学) Hong Kong University of Science and Technology(香港科技大学) Northeastern University(东北大学) Beijing University of Technology(北京理工大学)

AI总结 Jailbreak-AudioBench 通过构建工具箱、数据集和基准,深入评估大型音频语言模型中 jailbreak 威胁,并促进安全防护机制的发展。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.06851 2026-01-13 cs.AI

A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning

类脑协同核心在大语言模型中驱动行为与学习

Pedro Urbina-Rodriguez, Zafeirios Fountas, Fernando E. Rosas, Jun Wang, Andrea I. Luppi, Haitham Bou-Ammar, Murray Shanahan, Pedro A. M. Mediano

机构 * Department of Computing Imperial College London(帝国理工学院计算机系) Huawei Noah’s Ark Lab(华为诺亚实验室) AI Centre Department of Computer Science University College London(伦敦大学学院人工智能中心) Department of Informatics University of Sussex(Sussex大学信息学院) Centre for Complexity Science and Center for Psychedelic Research Department of Brain Science Imperial College London(帝国理工学院复杂科学中心和迷幻研究中心) Department of Psychiatry and Centre for Eudaimonia and Human Flourishing University of Oxford(牛津大学精神病学系和幸福与人类繁荣中心) Division of Information Engineering and St John’s College University of Cambridge(剑桥大学信息工程系和圣约翰学院) Montreal Neurological Institute McGill University(麦吉尔大学蒙特利尔神经科学研究所) Division of Psychology and Language Sciences University College London(伦敦大学学院心理学与语言科学系)

AI总结 本研究发现大语言模型中自发形成的协同核心与人脑相似,通过学习产生,影响行为与学习性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05774 2026-01-13 cs.AI

ConstraintLLM: A Neuro-Symbolic Framework for Industrial-Level Constraint Programming

ConstraintLLM: 一种用于工业级约束编程的神经符号框架

Weichun Shi, Minghao Liu, Wanting Zhang, Langchen Shi, Fuqi Jia, Feifei Ma, Jian Zhang

机构 * Hangzhou Institute for Advanced Study, UCAS, Hangzhou, China(杭州高等研究院,UCAS,杭州,中国) University of Oxford, Oxford, UK(牛津大学,牛津,英国) University of Science and Technology Beijing, Beijing, China(北京科技大学,北京,中国) SKLCS and Key Laboratory of System Software, ISCAS, Beijing, China(SKLCS和系统软件重点实验室,ISCAS,北京,中国) Laboratory of Parallel Software and Computational Science, ISCAS, Beijing, China(并行软件与计算科学实验室,ISCAS,北京,中国) University of Chinese Academy of Sciences, Beijing, China(中国科学院大学,北京,中国)

AI总结 ConstraintLLM是一种专为约束编程设计的神经符号框架,通过引入Constraint-Aware Retrieval Module和Tree-of-Thoughts框架,实现了在工业级约束编程基准上的高性能求解。

Comments Accepted to the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Main Conference

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 15999-16019

详情

展开后加载摘要…

URL PDF HTML 收藏