arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing

2026-05-18 至 2026-05-18 共收录 9
2605.16045 2026-05-18 cs.CL cs.AI cs.LG

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents

RecMem:基于递归的记忆巩固用于高效且有效的长运行LLM代理

Zijie Dai, Shiyuan Deng, Sheng Guan, Yizhou Tian, Xin Yao, Xiao Yan, James Cheng

机构 * Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程系) School of Computer Science, Beijing University of Posts and Telecommunications(北京邮电大学计算机学院) Huawei Cloud(华为云) Huawei Theory Lab(华为理论实验室) Institute for Math and AI, Wuhan University(武汉大学数学与人工智能研究院)

AI总结 RecMem通过递归机制优化内存巩固,减少token消耗并提升准确性,有效解决长运行LLM代理的内存管理问题。

Comments Accepted to ACL 2026 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16026 2026-05-18 cs.CL cs.AI

From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation

从平铺语言标签到类型学先验:面向多语言语音到语音翻译的结构化语言条件化

Yu Pan, Yang Hou, Xiongfei Wu, Liang Zhang, Yves Le Traon, Lei Ma, Jianjun Zhao

机构 * School of Information Science and Electrical Engineering, Kyushu University(九州大学信息科学与电子工程学院) Recho Inc.(Recho公司) National Institute of Informatics(国家信息研究所) Interdisciplinary Research Centre on Security, Reliability and Trust (SnT), University of Luxembourg(卢森堡大学安全、可靠性与信任跨学科研究中心) Donghua University(东华大学) Department of Computer Science, The University of Tokyo(东京大学计算机科学系) Department of Electrical and Computer Engineering, University of Alberta(阿尔伯塔大学电子与计算机工程系)

AI总结 本文提出S2ST-Omni 2框架,通过结构化类型学先验改进多语言语音到语音翻译,实验显示其在多个评估指标上表现优异,且在数据受限条件下仍能提升翻译效率。

Comments Submitted to IEEE/ACM TASLP. This work extends S2ST-Omni, accepted to Findings of ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.21251 2026-05-18 cs.LG cs.AI

CAP: Controllable Alignment Prompting for Unlearning in LLMs

CAP:用于大语言模型中去学习的可控对齐提示

Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian

机构 * School of Information and Software Engineering, University of Electronic Science and Technology of China(电子科技大学信息与软件学院)

AI总结 本文提出CAP框架,通过强化学习将去学习过程转化为可学习的提示优化,实现可控的去学习,无需更新模型参数,解决了现有方法的计算成本高、遗忘边界不可控等问题。

Comments Accpeted to ACL 2026 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.18145 2026-05-18 cs.CV cs.AI

Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework

基于3D医学影像的区域 grounded 报告生成:一个细粒度数据集和图增强框架

Cong Huy Nguyen, Son Dinh Nguyen, Guanlin Li, Tuan Dung Nguyen, Aditya Narayan Sankaran, Mai Huy Thong, Thanh Trung Nguyen, Mai Hong Son, Reza Farahbakhsh, Phi Le Nguyen, Noel Crespi

机构 * AI4LIFE, Hanoi University of Science and Technology, Vietnam(AI4LIFE,河内科学技术大学,越南) SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, France(SAMOVAR,Telecom SudParis,巴黎理工学院,法国) Military Central Hospital, Vietnam(108军区中央医院,越南)

AI总结 本文提出VietPET-RoI数据集和HiRRA框架,通过图增强模块捕捉RoI属性依赖,提升3D PET/CT报告生成的临床可靠性,实验表明其在BLEU、ROUGE-L和临床指标上均优于现有方法。

Comments 16 pages; Accepted to appear in ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05966 2026-05-18 cs.CL

FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures

FinReporting: 一种用于跨司法管辖区财务披露本地化报告的代理工作流

Fan Zhang, Mingzi Song, Rania Elbadry, Yankai Chen, Shaobo Wang, Yixi Zhou, Xunwen Zheng, Yueru He, Yuyang Dai, Georgi Georgiev, Ayesha Gull, Muhammad Usman Safder, Fan Wu, Liyuan Meng, Fengxian Ji, Junning Zhao, Xueqing Peng, Jimin Huang, Yu Chen, Xue, Liu, Preslav Nakov, Zhuohan Xie

机构 * MBZUAI The University of Tokyo(东京大学) Meiji Gakuin University(明治大学) McGill University(麦吉尔大学) Kyoto University(京都大学) Columbia University(哥伦比亚大学) University of California, Berkeley(加州大学伯克利分校)

AI总结 本文提出FinReporting,一种代理工作流,用于跨司法管辖区的财务披露本地化报告。该系统构建了涵盖损益表、资产负债表和现金流量表的统一本体,将报告分解为可审计的阶段,并通过约束验证器提升一致性和可靠性。

Comments Accepted at ACL 2026 Demo Track. 9 pages, including figures and tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15692 2026-05-18 cs.CL cs.LG

TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning

TemplateRL: 结构化模板引导的强化学习用于大语言模型推理

Jinyang Wu, Chonghua Liao, Mingkuan Feng, Shuai Zhang, Zhengqi Wen, Haoran Luo, Ling Yang, Huazhe Xu, Jianhua Tao

机构 * Tsinghua University(清华大学) Nanyang Technological University(南洋理工大学) Princeton University(普林斯顿大学) Shanghai AI Lab(上海人工智能实验室) Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心)

AI总结 TemplateRL通过结构化模板引导强化学习提升大语言模型推理能力,通过MCTS构建问题解决模板库并整合到RL训练中,提高轨迹命中率并减少无效探索,实验显示在AIME和AMC上表现优于GRPO。

Comments Accepted by ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15589 2026-05-18 cs.CL

MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models

MHGraphBench: 用于评估大语言模型中心理健康知识的图知识基准

Weixin Liu, Congning Ni, Shelagh A. Mulvaney, Susannah L. Rose, Murat Kantarcioglu, Bradley A. Malin, Zhijun Yin

机构 * Vanderbilt University(范德比大学) Vanderbilt University Medical Center(范德比大学医学院) Virginia Tech(弗吉尼亚理工学院)

AI总结 本文提出MHGraphBench基准,评估大语言模型在心理健康实体识别、关系判断及双跳推理能力,发现模型在实体类型识别和小关系类型判断上表现优异,但在关系预测和双跳推理上仍有不足,且输出格式可靠性对性能有显著影响。

Comments Accepted to GEM 2026, ACL 2026 Workshop; 9 pages main text plus references and appendices

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.14057 2026-05-18 cs.CL

Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents

双层级对话策略学习用于法律探究型对话代理

Xubo Lin, Zezhi Deng, Shihao Wang, Grace Hui Yang, Yang Deng

机构 * Georgetown University(乔治城大学) Singapore Management University(新加坡国立管理学院)

AI总结 本文提出双层级强化学习框架,用于法律场景中主动提取信息的对话代理,通过协调策略管理和细粒度生成,提升法律目标达成能力。

Comments Accepted in ACL 2026 as Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01089 2026-05-18 cs.AI

CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents

CodeDistiller:自动为科学编码代理生成代码库

Peter Jansen, Samiah Hassan, Pragnya Narasimha

机构 * University of Arizona(亚利桑那大学) Allen Institute for Artificial Intelligence(人工智能研究所)

AI总结 CodeDistiller通过自动提炼科学GitHub仓库代码,生成经过验证的领域特定代码库,提升科学发现系统实验的准确性与完整性。

Comments 8 pages, 3 figures, 3 tables. Accepted to ACL 2026 (Demo Track)

详情

展开后加载摘要…

URL PDF HTML 收藏