Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly
替换而非扩展:通过固定预算证据组装缓解多跳RAG中的上下文稀释
Moshe Lahmy, Roi Yozevitch
机构
*
Department of Electrical Engineering, Ariel University(电气工程系,阿里尔大学)
;
Department of Computer and Software Engineering, Ariel University(计算机与软件工程系,阿里尔大学)
Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
Ruiyi Yang, Hao Xue, Imran Razzak, Shirui Pan, Hakim Hacid, Flora D. Salim
机构
*
University of New South Wales(新南威尔士大学)
;
Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
;
Griffith University(格里菲斯大学)
;
Technology Innovation Institute(技术创新研究所)
机构
*
Peking University(北京大学)
;
Center for LLM, Institute for Advanced Algorithms Research(大模型中心,高级算法研究所)
;
Huazhong University of Science and Technology(华中科技大学)
CommentsThe authors have withdrawn this manuscript after identifying errors in the experimental analysis reported in Sections 3 and 4. These errors affect the reported relationship between answer presence and RAG rewriting gains and undermine the paper's main conclusions. Therefore, the results and conclusions in the current version should not be relied upon
机构
*
Department of Computer Science, University of Virginia, USA(弗吉尼亚大学计算机科学系)
;
National Library of Medicine, National Institutes of Health, USA(美国国立卫生研究院国家医学图书馆)
;
Department of Computer Science, University of Illinois Urbana–Champaign, USA(伊利诺伊大学厄巴纳-香槟分校计算机科学系)
;
Medical Oncology, Dana–Farber Cancer Institute, USA(达纳-法伯癌症研究所医学肿瘤科)
;
Surgery, University of Alabama at Birmingham, USA(阿拉巴马大学伯明翰分校外科系)
;
Department of Neurology, Yale School of Medicine, USA(耶鲁医学院神经病学系)
CommentsAccepted at Conference of the North American Chapter of the Association for Computational Linguistics, Student Research Workshop 2025 (NAACL SRW 2025)