期刊&会议

ACL

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

2025-10-06 至 2025-10-06 共收录 4 篇

2506.03887 2025-10-06 cs.CL

Pre$^3$: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation

Junyi Chen, Shihao Bai, Zaijun Wang, Siyu Wu, Chuheng Du, Hailong Yang, Ruihao Gong, Shengzhong Liu, Fan Wu, Guihai Chen

机构 * Shanghai Jiao Tong University（上海交通大学）； Beihang University（北京航空航天大学）； Sensetime Research（商汤科技研究院）

Comments Published as a conference paper at ACL 2025

2504.18243 2025-10-06 cs.LG

DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering

Rong Cheng, Jinyi Liu, Yan Zheng, Fei Ni, Jiazhen Du, Hangyu Mao, Fuzheng Zhang, Bo Wang, Jianye Hao

机构 * College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学）

Journal ref ACL 2025

2502.14837 2025-10-06 cs.CL cs.AI

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

Tao Ji, Bin Guo, Yuanbin Wu, Qipeng Guo, Lixing Shen, Zhan Chen, Xipeng Qiu, Qi Zhang, Tao Gui

机构 * School of Computer Science, Fudan University（复旦大学计算机科学学院）； School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）； Institute of Modern Languages and Linguistics, Fudan University（复旦大学现代语言与语言学研究所）； Institute of Trustworthy Embodied Artificial Intelligence, Fudan University（复旦大学可信具身人工智能研究所）； Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）； Pengcheng Laboratory（鹏城实验室）； Hikvision Inc（海康威视公司）

Comments 16 pages, 8 figures; Accepted to ACL 2025

2403.03923 2025-10-06 cs.CL

Did Translation Models Get More Robust Without Anyone Even Noticing?

Ben Peters, André F. T. Martins

机构 * Instituto de Telecomunicações（电信研究所）； Instituto Superior Técnico（技术高等学院）； Universidade de Lisboa（里斯本大学）； ELLIS Unit Lisbon (LUMLIS)（里斯本ELLIS单位（LUMLIS））； Unbabel

Comments ACL 2025 (Main) camera ready