All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所信息处理实验室);University of Chinese Academy of Sciences(中国科学院大学);MYbank, AntGroup(蚂蚁集团MYbank)
Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun
Multilingual Retrieval-Augmented Generation (mRAG) leverages cross-lingual evidence to ground Large Language Models (LLMs) in global knowledge. However, we show that current mRAG systems suffer from a language bias during reranking, systematically favoring English and the query's native language. By introducing an estimated oracle evidence analysis, we quantify a substantial performance gap between existing rerankers and the achievable upper bound. Further analysis reveals a critical distributional mismatch: while optimal predictions require evidence scattered across multiple languages, current systems systematically suppress such ``answer-critical'' documents, thereby limiting downstream generation performance. To bridge this gap, we propose \textit{\textbf{L}anguage-\textbf{A}gnostic \textbf{U}tility-driven \textbf{R}eranker \textbf{A}lignment (LAURA)}, which aligns multilingual evidence ranking with downstream generative utility. Experiments across diverse languages and generation models show that LAURA effectively mitigates language bias and consistently improves mRAG performance.
Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing(北京未来区块链与隐私计算先进创新中心);School of Artificial Intelligence, Beihang University(北航人工智能学院);Beijing Academy of Blockchain and Edge Computing(北京区块链与边缘计算研究院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
Johns Hopkins University Human Language Technology Center of Excellence(约翰霍普金斯大学人机语言技术卓越中心);University of Glasgow(格拉斯哥大学);Allen Institute for AI(人工智能研究院)
LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval
Apurba-NSU R&D Lab, Department of Electrical and Computer Engineering, North South University, Dhaka, Bangladesh(北南大学电气与计算机工程系,北南大学阿普尔巴-NSU研发实验室,达卡,孟加拉国);Apurba Technologies, Sunnyvale, CA 94085, USA(阿普尔巴技术公司,硅谷,加利福尼亚州,美国);Fordham University, New York, USA(福丁大学,纽约,美国)
RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校);City University of Hong Kong(香港城市大学);Virginia Tech(弗吉尼亚理工大学);University of South Florida(南佛罗里达大学);Rochester Institute of Technology(罗切斯特理工学院)
On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation
Center for Language and Cognition (CLCG), University of Groningen(格罗宁根大学语言与认知中心);Institute for Logic, Language and Computation (ILLC), University of Amsterdam(阿姆斯特丹大学逻辑、语言与计算研究所)
AI-VaxGuide: An Agentic RAG-Based LLM for Vaccination Decisions
Department of Fundamental Computing and its Applications, Faculty of NTIC(基础计算及其应用系);BIOSTIM Laboratory, Medicine Faculty Salah Boubnider Constantine 03 University(BIOSTIM实验室,医学系Salah Boubnider Constantine 03大学)
Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
Department of Computer Science, The University of Texas at Dallas(德克萨斯大学达拉斯分校计算机科学系);Department of Computer Science, University of California, Santa Barbara(加州大学圣巴巴拉分校计算机科学系)
Tatarstan Toponyms: A Bilingual Dataset and Hybrid RAG System for Geospatial Question Answering
Department of Data Analysis and Programming Technologies(数据分析与编程技术系);Institute of Computational Mathematics and Information Technologies(计算数学与信息科技学院);Kazan (Volga Region) Federal University(卡兹安(伏尔加地区)联邦大学)
Output Language Confusion under Multilingual Prompt Contamination
University of Tübingen(蒂宾根大学);Artificial Intelligence Institute, University of South Carolina(南卡罗来纳大学人工智能研究所);Thapar Institute of Engineering & Technology(塔帕尔工程技术学院);Indian Institute of Technology Kanpur(印度理工学院坎普尔分校);Indian AI Research Organization(印度人工智能研究组织)