RAG / 检索增强生成 - arXivDaily 专题

2410.18344 2024-10-25 cs.CL cs.AI cs.LG 84%

Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models

Fengchen Liu, Jordan Jung, Wei Feinstein, Jeff DAmbrogia, Gary Jung

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

2410.11494 2024-10-16 cs.CL cs.AI 84%

DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG

Jinyoung Kim, Dayoon Ko, Gunhee Kim

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

Comments EMNLP 2024 Main

2410.10136 2024-10-15 cs.CL cs.AI 84%

Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations

Garima Agrawal, Sashank Gummuluri, Cosimo Spera

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

2407.13998 2024-10-04 cs.CL cs.AI 84%

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering

Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

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

2406.06399 2024-08-06 cs.CL cs.AI 84%

Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue

Simone Alghisi, Massimo Rizzoli, Gabriel Roccabruna, Seyed Mahed Mousavi, Giuseppe Riccardi

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

Comments Accepted at INLG 2024

2310.11511 2023-10-19 cs.CL cs.AI cs.LG 84%

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi

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

Comments 30 pages, 2 figures, 12 tables

2304.13649 2023-04-27 cs.CV cs.CL cs.IR 84%

A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering

Alireza Salemi, Juan Altmayer Pizzorno, Hamed Zamani

专题命中知识库问答：dense retrieval(title,abstract)；retriever(abstract)；分类 cs.IR、cs.CL

2601.11255 2026-01-19 cs.CL cs.LG 84%

Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering

树状推理：改进多跳问题回答的检索增强生成

Yuling Shi, Maolin Sun, Zijun Liu, Mo Yang, Yixiong Fang, Tianran Sun, Xiaodong Gu

机构 * Shanghai Jiao Tong University（上海交通大学）； Shandong University（山东大学）； Carnegie Mellon University（卡内基梅隆大学）

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

AI总结 RT-RAG通过构建推理树来提升多跳问题回答的准确性和一致性，实验结果显示其在F1和EM指标上均优于现有方法。

Comments Accepted to GLOW@WWW2026. Code available at https://github.com/sakura20221/RT-RAG

2604.16915 2026-04-27 cs.CV 83%

KIRA: Knowledge-Intensive Image Retrieval and Reasoning Architecture for Specialized Visual Domains

KIRA：面向专业视觉领域的知识密集型图像检索与推理架构

Parthaw Goswami, Jaynto Goswami Deep

机构 * University of Missouri（密苏里大学）； SAP Prague（SAP 布拉格）

专题命中知识库问答：RAG(summary_cn,abstract)；retrieval augmented generation(abstract)

AI总结 KIRA提出一种五阶段框架，解决视觉RAG中的核心问题，包括多粒度知识库构建、领域自适应对比编码、双路径跨模态检索、多跳视觉推理及证据条件生成，通过四个专业领域实验验证其有效性。

Journal ref CVPR 2026 2nd Workshop on Knowledge-Intensive Multimodal Reasoning

2508.18093 2026-03-09 cs.CL 83%

Agri-Query: A Case Study on RAG vs. Long-Context LLMs for Cross-Lingual Technical Question Answering

Agri-Query：基于RAG与长上下文LLM在跨语言技术问答中的案例研究

Julius Gun, Timo Oksanen

机构 * Technical University of Munich, Germany Professorship of Agrimechatronics（慕尼黑技术大学教授职位，农业机电学教授）

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

AI总结本文通过Agri-Query案例研究，比较RAG与长上下文LLM在跨语言技术问答中的性能，发现混合RAG在准确性上优于直接提示方法。

Journal ref Technical University of Munich. 2026. ISBN 978-3-911430-11-1. https://mediatum.ub.tum.de/1845092

2510.07233 2026-03-03 cs.CL 83%

LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding

LAD-RAG：面向视觉丰富文档的布局感知动态RAG

Zhivar Sourati, Zheng Wang, Marianne Menglin Liu, Yazhe Hu, Mengqing Guo, Sujeeth Bharadwaj, Kyu Han, Tao Sheng, Sujith Ravi, Morteza Dehghani, Dan Roth

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

AI总结 LAD-RAG通过构建布局感知的文档图和动态检索机制，提升视觉丰富文档的检索与问答性能。

2602.22584 2026-02-27 cs.CL 83%

Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA

迈向可信的工业RAG：一种强化共适应框架用于广告问答

Wenwei Li, Ming Xu, Tianle Xia, Lingxiang Hu, Yiding Sun, Linfang Shang, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang

机构 * Tencent（腾讯）

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

AI总结本文提出了一种强化共适应框架，通过图感知检索和证据约束强化学习，提升工业广告问答的准确性、完整性和安全性，减少幻觉率。

2602.15898 2026-02-19 cs.CL 83%

MultiCube-RAG for Multi-hop Question Answering

多跳问答的MultiCube-RAG

Jimeng Shi, Wei Hu, Runchu Tian, Bowen Jin, Wonbin Kweon, SeongKu Kang, Yunfan Kang, Dingqi Ye, Sizhe Zhou, Shaowen Wang, Jiawei Han

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Korea University（韩国大学）

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

AI总结 MultiCube-RAG通过多维立方体结构实现多跳问答的高效推理与检索，提升响应准确率并增强可解释性。

Comments 12 pages

2602.15874 2026-02-19 cs.CL cs.LG 83%

P-RAG: Prompt-Enhanced Parametric RAG with LoRA and Selective CoT for Biomedical and Multi-Hop QA

P-RAG：结合LoRA和选择性CoT的增强型参数RAG

Xingda Lyu, Gongfu Lyu, Zitai Yan, Yuxin Jiang

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

AI总结 P-RAG通过LoRA和选择性CoT提升生物医学问答的准确性和可扩展性。

Journal ref Proceedings of International Conference on Computing and Data Science Symposium: Application of Machine Learning in Engineering, 2025

2602.05195 2026-02-11 cs.AI 83%

Traceable Cross-Source RAG for Chinese Tibetan Medicine Question Answering

可追溯的多源RAG用于藏医药问答

Fengxian Chen, Zhilong Tao, Jiaxuan Li, Yunlong Li, Qingguo Zhou

机构 * School of Information Science & Engineering, Lanzhou University（信息科学与工程学院，兰州大学）

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

AI总结本文提出DAKS和对齐图方法，用于提升多源RAG在藏医药问答中的可追溯性、减少幻觉并增强跨知识库验证能力。

2505.13258 2026-01-30 cs.CL 83%

Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning

迈向透明的RAG：通过强化学习促进LLM生成中的证据可追溯性

Jingyi Ren, Yekun Xu, Xiaolong Wang, Weitao Li, Ante Wang, Weizhi Ma, Yang Liu

机构 * DCST \& AIR, Tsinghua University Beijing, China ； DCST, Tsinghua University Beijing, China ； AIR, Tsinghua University Beijing, China ； DSCT \& AIR, Tsinghua University Beijing, China ； DCST \& AIR, Tsinghua University ； DCST, Tsinghua University ； AIR, Tsinghua University ； DSCT \& AIR, Tsinghua University

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

AI总结 TRACE通过强化学习提升LLM生成中的证据可追溯性，实现透明输出和准确性提升。

2504.08231 2026-01-28 cs.CL 83%

Out of Style: RAG's Fragility to Linguistic Variation

脱离风格：RAG对语言变异的脆弱性

Tianyu Cao, Neel Bhandari, Akhila Yerukola, Akari Asai, Maarten Sap

机构 * Language Technologies Institute, Carnegie Mellon University（语言技术研究所，卡内基梅隆大学）

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

AI总结本研究分析了RAG系统在不同语言变异维度下的性能，发现其在非正式和语法错误查询中表现显著下降，凸显了对语言变化的脆弱性。

Comments Accepted to EACL 2026 (Main Conference)

2601.07054 2026-01-13 cs.CL cs.LG 83%

Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge

基于新知识的多跳问答中微调与RAG的比较

Zhuoyi Yang, Yurun Song, Iftekhar Ahmed, Ian Harris

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

AI总结本文比较了微调与RAG在多跳问答中处理新颖知识的效果，发现RAG在时间新颖信息问答中表现更优，而有监督微调整体准确率最高。

2601.06922 2026-01-13 cs.CL 83%

TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG

TreePS-RAG: 基于树的强化学习过程监督在代理RAG中的应用

Tianhua Zhang, Kun Li, Junan Li, Yunxiang Li, Hongyin Luo, Xixin Wu, James Glass, Helen Meng

机构 * The Chinese University of Hong Kong, Hong Kong SAR, China（香港中文大学）； Massachusetts Institute of Technology, Cambridge MA, USA（麻省理工学院）

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

AI总结 TreePS-RAG通过基于树的在线强化学习框架，在代理RAG中实现细粒度过程监督，提升多跳和通用问答任务性能。

2412.14191 2025-11-26 cs.CY cs.AI 83%

Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education

面向本体的RAG用于提升网络安全教育中的问答系统

Chengshuai Zhao, Garima Agrawal, Fan Zhang, Tharindu Kumarage, Zhen Tan, Yuli Deng, Ying-Chih Chen, Huan Liu

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

AI总结本文提出CyberRAG，一种面向本体的检索增强生成方法，用于提升网络安全教育中问答系统的可靠性与准确性。

Comments Accepted by the 2025 IEEE International Conference on Big Data (IEEE BigData 2025)

2511.09831 2025-11-14 cs.CL cs.CY 83%

Answering Students' Questions on Course Forums Using Multiple Chain-of-Thought Reasoning and Finetuning RAG-Enabled LLM

Neo Wang, Sonit Singh

机构 * School of Computer Science and Engineering, University of New South Wales, Sydney, Australia（计算机科学与工程学院，新南威尔士大学，悉尼，澳大利亚）

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

Comments 8 pages

2511.04560 2025-11-07 cs.CL 83%

BanglaMedQA and BanglaMMedBench: Evaluating Retrieval-Augmented Generation Strategies for Bangla Biomedical Question Answering

Sadia Sultana, Saiyma Sittul Muna, Mosammat Zannatul Samarukh, Ajwad Abrar, Tareque Mohmud Chowdhury

机构 * Department of Computer Science and Engineering, Islamic University of Technology（计算机科学与工程系，伊斯兰技术大学）

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

Comments Under Review

2509.00877 2025-10-17 cs.CL 83%

EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes

Yuqin Dai, Guoqing Wang, Yuan Wang, Kairan Dou, Kaichen Zhou, Zhanwei Zhang, Shuo Yang, Fei Tang, Jun Yin, Pengyu Zeng, Zhenzhe Ying, Can Yi, Changhua Meng, Yuchen Zhou, Yongliang Shen, Shuai Lu

机构 * Tsinghua University（清华大学）； Zhejiang University（浙江大学）； Ant Group（蚂蚁集团）； Massachusetts Institute of Technology（麻省理工学院）； UC Berkeley（加州大学伯克利分校）； The University of Hong Kong（香港大学）； National University of Singapore（新加坡国立大学）

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

2509.08596 2025-09-11 cs.CL 83%

LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge

Dima Galat, Diego Molla-Aliod

机构 * University of Technology Sydney (UTS), Australia（悉尼技术大学（UTS））

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

Comments CEUR-WS, CLEF2025

2506.07042 2025-08-26 cs.CL 83%

Reasoning with RAGged events: RAG-Enhanced Event Knowledge Base Construction and reasoning with proof-assistants

Stergios Chatzikyriakidis

机构 * Computational Linguistics and Language Technology lab（计算语言学与语言技术实验室）； Department of Philology（文学系）； University of Crete（克里特大学）

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

2505.17326 2025-08-08 cs.IR cs.SD eess.AS 83%

VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering

Zackary Rackauckas, Julia Hirschberg

机构 * Columbia University（哥伦比亚大学）

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

Comments Accepted to ACL 2025 Workshop MAGMaR

Journal ref Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025), pp. 40-46, Vienna, Austria, August 2025. Association for Computational Linguistics

2508.01990 2025-08-05 cs.CL 83%

Contextually Aware E-Commerce Product Question Answering using RAG

Praveen Tangarajan, Anand A. Rajasekar, Manish Rathi, Vinay Rao Dandin, Ozan Ersoy

机构 * Flipkart US R\&D Center Bellevue Washington USA ； Flipkart US R\&D Center

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

Comments 6 pages, 1 figure, 5 tables. Preprint under review

2506.22852 2025-07-01 cs.CL 83%

Knowledge Augmented Finetuning Matters in both RAG and Agent Based Dialog Systems

Yucheng Cai, Yuxuan Wu, Yi Huang, Junlan Feng, Zhijian Ou

机构 * EE Department, Tsinghua University（清华大学电子工程系）； China Mobile Research Institute（中国移动研究院）

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

2410.15805 2025-06-04 cs.AI 83%

RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance

Tianyang Zhang, Zhuoxuan Jiang, Shengguang Bai, Tianrui Zhang, Lin Lin, Yang Liu, Jiawei Ren

机构 * Shanghai Business School（上海商学院）； University of North Carolina Greensboro（北卡罗来纳州格林斯堡大学）； Skema Business School（Skema商学院）； North Carolina Central University（北卡罗来纳州立大学）

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

Comments Accepted by EMNLP 2024 Industry Track

2506.00232 2025-06-03 cs.CL 83%

ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering

Ruofan Wu, Youngwon Lee, Fan Shu, Danmei Xu, Seung-won Hwang, Zhewei Yao, Yuxiong He, Feng Yan

机构 * University of Houston（德克萨斯大学休斯敦分校）； Seoul National University（首尔国立大学）； Snowflake AI Research（Snowflake人工智能研究）

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

1. 知识库问答 543 篇

Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models

DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG

Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering

Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering

Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering

KIRA: Knowledge-Intensive Image Retrieval and Reasoning Architecture for Specialized Visual Domains

Agri-Query: A Case Study on RAG vs. Long-Context LLMs for Cross-Lingual Technical Question Answering

LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding

Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA

MultiCube-RAG for Multi-hop Question Answering

P-RAG: Prompt-Enhanced Parametric RAG with LoRA and Selective CoT for Biomedical and Multi-Hop QA

Traceable Cross-Source RAG for Chinese Tibetan Medicine Question Answering

Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning

Out of Style: RAG's Fragility to Linguistic Variation

Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge

TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG

Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education

Answering Students' Questions on Course Forums Using Multiple Chain-of-Thought Reasoning and Finetuning RAG-Enabled LLM

BanglaMedQA and BanglaMMedBench: Evaluating Retrieval-Augmented Generation Strategies for Bangla Biomedical Question Answering

EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes

LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge

Reasoning with RAGged events: RAG-Enhanced Event Knowledge Base Construction and reasoning with proof-assistants

VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering

Contextually Aware E-Commerce Product Question Answering using RAG

Knowledge Augmented Finetuning Matters in both RAG and Agent Based Dialog Systems

RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance

ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering