arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

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

2025-09-03 至 2025-09-03 共收录 11
2505.24671 2025-09-03 cs.CL cs.AI

Multiple LLM Agents Debate for Equitable Cultural Alignment

Dayeon Ki, Rachel Rudinger, Tianyi Zhou, Marine Carpuat

机构 * University of Maryland(马里兰大学)

Comments ACL 2025 (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11582 2025-09-03 cs.CL

AskQE: Question Answering as Automatic Evaluation for Machine Translation

Dayeon Ki, Kevin Duh, Marine Carpuat

机构 * University of Maryland(马里兰大学) Johns Hopkins University(约翰霍普金斯大学)

Comments ACL 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.09146 2025-09-03 cs.CV cs.MM

Generative Frame Sampler for Long Video Understanding

Linli Yao, Haoning Wu, Kun Ouyang, Yuanxing Zhang, Caiming Xiong, Bei Chen, Xu Sun, Junnan Li

机构 * National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University(国家多媒体信息处理重点实验室,计算机学院,北京大学) Peking University(北京大学) Salesforce Research(Salesforce 研究) Independent Researcher(独立研究者)

Comments ACL 2025 Findings. Code: https://github.com/yaolinli/GenS

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.12122 2025-09-03 cs.LG

Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA

Patryk Marszałek, Klaudia Bałazy, Jacek Tabor, Tomasz Kuśmierczyk

机构 * Jagiellonian University(雅盖隆大学)

Comments Accepted to Findings of the Association for Computational Linguistics: EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.05790 2025-09-03 cs.AI cs.HC cs.LG

Understanding Impact of Human Feedback via Influence Functions

Taywon Min, Haeone Lee, Yongchan Kwon, Kimin Lee

机构 * KAIST(韩国科学技术院) Columbia University(哥伦比亚大学)

Comments Accepted at ACL 2025, Source code: https://github.com/mintaywon/IF_RLHF

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics 63 (2025) 27471-27500

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.03679 2025-09-03 cs.CL

Evaluating Language Models as Synthetic Data Generators

Seungone Kim, Juyoung Suk, Xiang Yue, Vijay Viswanathan, Seongyun Lee, Yizhong Wang, Kiril Gashteovski, Carolin Lawrence, Sean Welleck, Graham Neubig

机构 * Carnegie Mellon University(卡内基梅隆大学) KAIST AI(韩国科学技术院人工智能研究所) University of Washington(华盛顿大学) NEC Laboratories Europe(NEC欧洲实验室) Ss. Cyril and Methodius University of Skopje(斯科普里塞奥尼和方法ius大学)

Comments ACL 2025 (main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.15664 2025-09-03 cs.CL cs.AI

Mitigating Semantic Leakage in Cross-lingual Embeddings via Orthogonality Constraint

Dayeon Ki, Cheonbok Park, Hyunjoong Kim

机构 * University of Maryland(马里兰大学) NAVER Cloud(NAVER云)

Comments ACL 2024 RepL4NLP Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.10722 2025-09-03 cs.CL cs.AI

MEGen: Generative Backdoor into Large Language Models via Model Editing

Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang, Hai Zhao, Yun Li, Qianren Wang

机构 * School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院) Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University(上海交通大学智能交互与认知工程重点实验室) Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3(上海Web3可信数据流通与治理重点实验室) Cognitive AI Lab(认知人工智能实验室)

Comments ACL 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00629 2025-09-03 cs.CL

Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?

Md Tanzib Hosain, Md Kishor Morol

机构 * American International University-Bangladesh(美国国际大学(Bangladesh)) Cornell University(康奈尔大学) ELITE Research Lab(ELITE研究实验室)

Comments Accepted in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Student Research Workshop), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04836 2025-09-03 cs.CY cs.AI

Oversight Structures for Agentic AI in Public-Sector Organizations

Chris Schmitz, Jonathan Rystrøm, Jan Batzner

机构 * Centre for Digital Governance, Hertie School(数字治理中心,赫尔姆斯学校) Oxford Internet Institute, University of Oxford(牛津互联网研究所,牛津大学) Weizenbaum Institute Berlin, Germany(贝伦贝格Weizenbaum研究所) Technical University Munich, Germany(慕尼黑技术大学)

Comments To appear at REALM@ACL2025

Journal ref Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025), pages 298-308, Vienna, Austria. Association for Computational Linguistics

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.07268 2025-09-03 cs.MM cs.CL cs.CV

Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation

Jinyuan Li, Ziyan Li, Han Li, Jianfei Yu, Rui Xia, Di Sun, Gang Pan

机构 * College of Intelligence and Computing, Tianjin University(智能与计算学院,天津大学) NJUST(南京理工大学) College of Mathematics, Taiyuan University of Technology(数学学院,太原科技大学) Tianjin University of Science and Technology(天津科技大学)

Comments Extension of our Findings of EMNLP 2023 & ACL 2024 paper, IEEE Transactions on Multimedia accepted on July 19, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏