arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing

2026-01-13 至 2026-01-13 共收录 4
2510.03405 2026-01-13 cs.MA cs.AI cs.CR

LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits

LegalSim:多智能体法律系统模拟以发现程序性漏洞

Sanket Badhe

机构 * Rutgers University(罗切斯特大学)

AI总结 LegalSim通过多智能体模拟揭示法律程序中的漏洞链,通过PPO、老虎机、LLM和启发式策略比较,发现AI系统如何利用程序性弱点。

Comments 12 pages with 2 figures, accepted at the NLLP workshop at EMNLP 2025

Journal ref Proceedings of the Natural Legal Language Processing Workshop 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.03989 2026-01-13 cs.CL

Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models

更强的检索增强生成基线:长上下文语言模型

Alex Laitenberger, Christopher D. Manning, Nelson F. Liu

机构 * Stanford University(斯坦福大学)

AI总结 本文提出DOS RAG作为长上下文问答任务的强基线,通过保持文档结构和简单性,在多个基准上超越复杂方法。

Comments 11 pages, 6 figures, for associated source code, see https://github.com/alex-laitenberger/stronger-baselines-rag

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), pages 32559-32569

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.04472 2026-01-13 cs.LG cs.AI

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models

DAST: 为大推理模型引入难度自适应的慢思考

Yi Shen, Jian Zhang, Jieyun Huang, Shuming Shi, Wenjing Zhang, Jiangze Yan, Ning Wang, Kai Wang, Zhaoxiang Liu, Shiguo Lian

机构 * Unicom Data Intelligence(中国unicom数据智能) Data Science & Artificial Intelligence Research Institute(数据科学与人工智能研究院)

AI总结 DAST通过自适应调整推理步骤长度,有效减少大模型的过度思考问题,同时保持复杂任务的推理准确性。

Comments EMNLP 2025 Industry Track

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