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~~

AI 大模型

RAG / 检索增强生成

检索增强生成、向量检索、知识库问答和面向大模型的搜索系统。

共收录 8572 信号源:cs.IR, cs.CL, cs.AI, cs.DB

1. 知识库问答 545 篇

2405.19207 2024-05-30 cs.IR cs.AI 86%

A Multi-Source Retrieval Question Answering Framework Based on RAG

Ridong Wu, Shuhong Chen, Xiangbiao Su, Yuankai Zhu, Yifei Liao, Jianming Wu

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);knowledge retrieval(abstract);分类 cs.IR、cs.AI

Comments 4 pages,3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.18825 2026-07-22 cs.CL cs.AI cs.IR 新提交 86%

AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System

AILQA:评估适用于印度法律体系的人工智能驱动的法律问答系统

Shubham Kumar Nigam, Shubham Kumar Mishra, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya

机构 * Indian Institute of Technology(印度理工学院) Symbiosis Law School(共生法学院) Indian Institute of Science Education and Research(印度科学教育与研究学院) University of Birmingham(伯明翰大学)

专题命中 知识库问答 :RAG(summary_cn,abstract);retrieval-augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

AI总结 该研究针对印度法律体系开发AILQA系统,利用多种模型应对挑战,通过严格评估强调RAG范式提升答案质量,评估其在标准化测试中的表现,讨论挑战并给出未来研究方向,为增强法律决策支持系统助力。

Comments Accepted in AI and Law Journal

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.25621 2025-10-30 cs.CL cs.AI cs.IR 86%

FARSIQA: Faithful and Advanced RAG System for Islamic Question Answering

Mohammad Aghajani Asl, Behrooz Minaei Bidgoli

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract,comments);分类 cs.IR、cs.CL、cs.AI

Comments 37 pages, 5 figures, 10 tables. Keywords: Retrieval-Augmented Generation (RAG), Question Answering (QA), Islamic Knowledge Base, Faithful AI, Persian NLP, Multi-hop Reasoning, Large Language Models (LLMs)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.16409 2026-06-16 cs.CL 新提交 85%

PathRouter: Aligning Rewards with Retrieval Quality in Agentic Graph Retrieval-Augmented Generation

PathRouter: 在智能体图检索增强生成中对齐奖励与检索质量

Bo Wang, Heyan Huang, Yaolin Li, Wei Tang, Yuan Zhang, Wenbo Li, Mingze Gao, Ge Shi, Chong Feng

机构 * Beijing Institute of Technology(北京理工大学) Joy Future Academy(京东探索研究院)

专题命中 知识库问答 :RAG(summary_cn,abstract_cn);retrieval-augmented generation(title);分类 cs.CL

AI总结 针对智能体图RAG中答案路径奖励混淆和搜索更新模糊问题,提出PathRouter框架,通过路径感知训练联合评估答案正确性与证据路径重叠,并引入冻结金证据教师提供token级KL指导,在六个QA基准上显著提升F1和证据路径重叠。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12975 2026-05-14 cs.AI 85%

Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation

检索成本低廉,展示代码:可执行多跳推理的检索增强生成

Jiashuo Sun, Jimeng Shi, Yixuan Xie, Saizhuo Wang, Jash Rajesh Parekh, Pengcheng Jiang, Zhiyi Shi, Jiajun Fan, Qinglong Zheng, Peiran Li, Shaowen Wang, Ge Liu, Jiawei Han

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Hong Kong University of Science and Technology(香港科学与技术大学) Texas A&M University(德克萨斯农工大学)

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract,abstract_cn);分类 cs.AI

AI总结 本文提出PyRAG框架,将多跳检索增强生成转化为程序合成与执行,通过可执行Python代码实现可调试的推理过程,提升多跳问答性能。

Comments 32 pages, 20 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16988 2025-09-03 cs.IR 85%

RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering

Ines Besrour, Jingbo He, Tobias Schreieder, Michael Färber

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract);hybrid retrieval(abstract);分类 cs.IR

Comments Accepted at SIGIR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03110 2025-08-06 cs.CL 85%

Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation

Zizhong Li, Haopeng Zhang, Jiawei Zhang

机构 * University of California, Davis(加州大学戴维斯分校) University of Hawaii at Mānoa(夏威夷大学马诺阿分校)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);retriever(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.01717 2024-02-07 cs.CL cs.AI cs.IR 85%

From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance Process

Jaewoong Kim, Moohong Min

专题命中 知识库问答 :RAG(title,abstract);retrieval augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

Comments Total number of pages: 9. Total number of figures: 2. For the source code and experimental results of this paper, see https://github.com/jwoongkim11/QA-RAG. For the dataset used in training and evaluating the model, see https://huggingface.co/datasets/Jaymax/FDA Pharmaceuticals FAQ

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03489 2025-08-06 cs.CL cs.AI 85%

CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation

Kaiwen Zhao, Bharathan Balaji, Stephen Lee

机构 * University of Pittsburgh(匹兹堡大学) Amazon(亚马逊)

专题命中 知识库问答 :retrieval-augmented generation(title);RAG(title);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22841 2026-07-28 cs.IR cs.AI cs.CL 新提交 85%

Language-Routed RAG and Direct Option Scoring for Multilingual Financial QA: DS@GT at FinMMEval

用于多语言金融问答的语言路由RAG和直接选项评分:FinMMEval上的DS@GT

Justice Ayela, Kabir Sahni

专题命中 知识库问答 :RAG(title,title_cn);分类 cs.IR、cs.CL、cs.AI

AI总结 该研究针对多语言金融问答基准FinMMEval 2026任务1,构建基于LangGraph的检索增强管道,用RADS评分,通过加权倒数排名融合低资源语言索引,采用语言路由选择模型,揭示语言感知检索等对多语言金融推理的重要性。

Comments Accepted for publication in the CLEF 2026 Working Notes. 15 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25039 2026-05-26 cs.CV 85%

AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy

AstroRAG -- 一种基于PageRank的检索增强生成管道用于天文学问答

Zhifeng Wang, Jason Jingshi Li, Kaihao Zhang, Ramesh Sankaranarayana

机构 * Australian National University(澳大利亚国立大学) Learning Machines Pty Ltd

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract,abstract_cn)

AI总结 提出AstroRAG,一种基于PageRank的检索增强生成管道,通过两阶段检索(MMR和PR重排序)在严格token预算下选择紧凑互支持的上下文,无需训练且保护隐私,在天文学QA基准上使Mistral-7B准确率和F1分数达到79.49%,性能近乎翻倍。

Comments Accepted to IEEE CAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.09552 2026-02-11 cs.CL cs.AI cs.IR 85%

Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA

跨多领域对话问答中RAG方法的全面比较

Klejda Alushi, Jan Strich, Chris Biemann, Martin Semmann

机构 * Hub of Computing and Data Science (HCDS) University of Hamburg(计算与数据科学中心(HCDS)乌姆斯大学)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

AI总结 本文通过跨多领域对话问答数据集的全面比较,发现简单策略在多轮对话中表现更优,而复杂方法未必有效,强调检索策略与数据集结构的匹配至关重要。

Comments Accepted to EACL SRW 26

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.25052 2026-01-01 cs.CL cs.AI cs.IR 85%

AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG

AdaGReS:基于冗余感知评分的自适应贪心上下文选择用于带有令牌预算的RAG

Chao Peng, Bin Wang, Zhilei Long, Jinfang Sheng

机构 * Central South University(中南大学) Yizhi Intelligent (YZInt)(义智智能(YZInt))

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

AI总结 AdaGReS通过冗余感知评分和贪心选择优化,提升RAG在令牌预算下的上下文质量与生成效果。

Comments Preprint. Under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22442 2025-12-30 cs.CL cs.AI cs.IR cs.LG 85%

HiFi-RAG: Hierarchical Content Filtering and Two-Pass Generation for Open-Domain RAG

HiFi-RAG:面向开放域RAG的分层内容过滤与双阶段生成

Cattalyya Nuengsigkapian

机构 * Google(谷歌)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

AI总结 HiFi-RAG通过分层过滤和双阶段生成方法,在开放域RAG中提升答案生成质量,实现ROUGE-L和DeBERTaScore的显著提升。

Comments A winning solution for the NeurIPS 2025 MMU-RAGent Competition (Closed-Source Text-to-Text Static Evaluation)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.05119 2025-12-08 cs.IR cs.AI cs.CL 85%

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering

RAG-IGBench: 用于开放领域问答中基于检索增强生成的交错生成的创新评估

Rongyang Zhang, Yuqing Huang, Chengqiang Lu, Qimeng Wang, Yan Gao, Yi Wu, Yao Hu, Yin Xu, Wei Wang, Hao Wang, Enhong Chen

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学) Xiaohongshu Inc.(小红书公司) Xi’an Jiaotong University(西安交通大学)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

AI总结 RAG-IGBench通过创新的评估指标和多模态数据,评估基于检索增强生成的交错生成任务,验证了模型在开放领域问答中的性能提升。

Comments 26 pages, 6 figures, NeurIPS 2025 D&B Track poster

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01643 2025-11-04 cs.CL cs.AI cs.IR 85%

A Graph-based RAG for Energy Efficiency Question Answering

Riccardo Campi, Nicolò Oreste Pinciroli Vago, Mathyas Giudici, Pablo Barrachina Rodriguez-Guisado, Marco Brambilla, Piero Fraternali

机构 * Politecnico di Milano, DEIB Department(米兰Politecnico大学DEIB部门) Voltiva Energy(Voltiva能源公司)

专题命中 知识库问答 :RAG(title,abstract);retrieval augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

Journal ref Verma, H., Bozzon, A., Mauri, A., Yang, J. (eds) Web Engineering. ICWE 2025. Lecture Notes in Computer Science, vol 15749. Springer, Cham

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14400 2025-10-21 cs.CL cs.AI cs.IR 85%

MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering

Yingpeng Ning, Yuanyuan Sun, Ling Luo, Yanhua Wang, Yuchen Pan, Hongfei Lin

机构 * College of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院) Air Force Communications NCO Academy(空军通信NCO学院)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.IR、cs.CL、cs.AI

Comments Accepted as a short paper at BlBM2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.04716 2025-09-08 cs.CL cs.AI cs.IR 85%

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering

Yushi Sun, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract);分类 cs.IR、cs.CL、cs.AI

Comments Accepted by EMNLP Findings 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01883 2025-04-03 cs.AI cs.CL cs.IR cs.LG 85%

CoRAG: Collaborative Retrieval-Augmented Generation

Aashiq Muhamed, Mona Diab, Virginia Smith

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract);分类 cs.IR、cs.CL、cs.AI

Comments NAACL 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.22353 2025-02-18 cs.IR cs.AI cs.CL 85%

RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering

Zhongwu Chen, Chengjin Xu, Dingmin Wang, Zhen Huang, Yong Dou, Xuhui Jiang, Jian Guo

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract);分类 cs.IR、cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05197 2026-03-17 cs.AI cs.CL cs.CV 84%

QA-Dragon: Query-Aware Dynamic RAG System for Knowledge-Intensive Visual Question Answering

QA-Dragon:面向知识密集型视觉问答的查询感知动态RAG系统

Zhuohang Jiang, Pangjing Wu, Xu Yuan, Wenqi Fan, Qing Li

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.CL、cs.AI;retrieval augmented generation(journal_ref)

AI总结 QA-Dragon通过引入领域路由器和搜索路由器,实现多模态、多轮和多跳推理,提升复杂视觉问答任务的推理性能,实验显示其在单源、多源和多轮任务中均优于基线模型。

Comments The source code for our system is released in https://github.com/jzzzzh/QA-Dragon

Journal ref 2025 KDD Cup Workshop for Multimodal Retrieval Augmented Generation

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.10921 2026-08-07 cs.CL 版本更新 84%

Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering

仅追踪所需:面向长文档问答的结构感知按需超图记忆

Xiangjun Zai, Xingyu Tan, Chen Chen, Xiaoyang Wang, Wenjie Zhang

机构 * University of New South Wales(新南威尔士大学) CSIRO(澳大利亚联邦科学与工业研究组织) University of Wollongong(伍伦贡大学)

专题命中 知识库问答 :RAG(summary_cn,abstract);retrieval-augmented generation(abstract);分类 cs.CL

AI总结 提出DocTrace,一种多智能体RAG框架,通过查询触发的知识组织、文档结构感知和经验引导推理,解决长文档问答中知识组织成本高、结构利用不足和推理经验无法复用的问题,在三个数据集上取得最佳性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00765 2026-08-04 cs.CL 新提交 84%

RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation

RAGOCR:基于视觉表征的检索增强文本光学压缩

Jiayang Yu, Jialun Zhong, Lei Zou

机构 * Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所)

专题命中 知识库问答 :RAG(summary_cn,abstract);retrieval-augmented generation(abstract);分类 cs.CL

AI总结 该研究针对RAG压缩的权衡问题,提出RAGOCR框架,通过查询感知动态分辨率机制压缩检索文档为视觉表征,在五个QA基准上实现比朴素RAG更高准确率和更低token需求,且优于各类压缩基线。

Comments Under reviewing

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.14751 2026-04-17 cs.CL 84%

Query pipeline optimization for cancer patient question answering systems

癌症患者问答系统中的查询管道优化

Maolin He, Rena Gao, Mike Conway, Brian E. Chapman

机构 * School of Computing and Information Systems, University of Melbourne(墨尔本大学计算与信息系统学院) Health Data Science and Biostatistics, University of Texas Southwestern Medical Center(德克萨斯西南医学中心健康数据科学与生物统计学)

专题命中 知识库问答 :RAG(summary_cn,abstract);retrieval-augmented generation(abstract);分类 cs.CL

AI总结 本文提出了一种针对癌症患者问答系统的RAG查询管道三方面优化方法,通过改进文档检索、段落检索和语义表示,提升了回答准确性。

Comments This paper has been accepted as a Findings Paper in ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.03616 2026-03-31 cs.CL cs.AI 84%

Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task

多语言检索增强生成用于知识密集型任务

Leonardo Ranaldi, Barry Haddow, Alexandra Birch

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract);分类 cs.CL、cs.AI

AI总结 本文研究多语言检索增强生成在开放域问答中的有效性,提出tRAG和MultiRAG方法,发现tRAG覆盖有限,MultiRAG效率高但存在不一致,CrossRAG通过翻译文档到共同语言提升性能。

Journal ref 2026.findings-eacl.35

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13557 2026-02-13 cs.IR cs.AI 84%

AMAQA: A Metadata-based QA Dataset for RAG Systems

AMAQA:基于元数据的问答数据集用于RAG系统

Davide Bruni, Marco Avvenuti, Nicola Tonellotto, Maurizio Tesconi

机构 * Institute for Informatics and Telematics, National Research Council(信息与电信研究院,国家研究院) Department of Information Engineering, University of Pisa(信息工程系,比萨大学) Department of Computer Science, University of Pisa(计算机科学系,比萨大学)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.IR、cs.AI

AI总结 AMAQA是首个整合元数据的单跳问答基准测试,通过结合文本和元数据提升问答系统性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.04711 2026-02-06 cs.IR cs.AI 84%

Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention

通过稀疏注意力缓解RAG中的语料知识污染攻击

Sagie Dekel, Moshe Tennenholtz, Oren Kurland

机构 * Faculty of Data and Decision Sciences, Technion - Israel Institute of Technology, Haifa, Israel(数据与决策科学学院,技术Ion-以色列理工学院,海法,以色列)

专题命中 知识库问答 :RAG(title,abstract);retrieval augmented generation(abstract);分类 cs.IR、cs.AI

AI总结 本文提出SDAG方法,通过稀疏注意力机制有效防御RAG中的语料知识污染攻击,显著提升防御性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12658 2026-01-27 cs.CL cs.AI 84%

Augmenting Question Answering with A Hybrid RAG Approach

通过混合RAG方法增强问答

Tianyi Yang, Nashrah Haque, Vaishnave Jonnalagadda, Yuya Jeremy Ong, Zhehui Chen, Yanzhao Wu, Lei Yu, Divyesh Jadav, Wenqi Wei

机构 * Plastic Lab(塑料实验室) Google(谷歌) Florida International University(佛罗里达国际大学) Rensselaer Polytechnic Institute(伦塞拉尔理工学院)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.CL、cs.AI

AI总结 本文提出SSRAG方法,通过混合查询增强、代理路由和结构化检索技术,提升问答任务的响应质量。

Comments 10 pages, 5 tables, 2 figures; presented at IEEE CogMI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.16787 2026-01-13 cs.CL cs.AI 84%

Credible Plan-Driven RAG Method for Multi-Hop Question Answering

可信计划驱动的RAG方法用于多跳问答

Ningning Zhang, Chi Zhang, Zhizhong Tan, Xingxing Yang, Weiping Deng, Wenyong Wang

机构 * Macau University of Science and Technology(澳门科学技术大学)

专题命中 知识库问答 :RAG(title,abstract);retrieval-augmented generation(abstract);分类 cs.CL、cs.AI

AI总结 PAR-RAG通过引入复杂性感知的计划生成和双验证机制,提升了多跳问答任务中的推理稳定性和事实一致性,实现了更可靠的问答性能。

Comments 24 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10900 2025-11-20 cs.CL cs.AI 84%

Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering

Xueren Ge, Sahil Murtaza, Anthony Cortez, Homa Alemzadeh

专题命中 知识库问答 :retrieval-augmented generation(title,abstract);RAG(abstract);分类 cs.CL、cs.AI

Comments Accepted by AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏