RAG / 检索增强生成

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems

连点成线：知识图谱引导的爬虫攻击对抗检索增强生成系统

Mengyu Yao, Ziqi Zhang, Ning Luo, Shaofei Li, Yifeng Cai, Xiangqun Chen, Yao Guo, Ding Li

机构 * MOE Key Lab of HCST (PKU), School of Computer Science, Peking University（信息与电子技术教育部重点实验室（北京大学）、计算机科学学院、北京大学） ； Department of Computer Science, University of Illinois Urbana-Champaign（计算机科学系、伊利诺伊大学厄巴纳-香槟分校） ； Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign（电气与计算机工程系、伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.IR、cs.AI

AI总结 RAGCrawler通过知识图谱引导的攻击方法，有效提升RAG系统知识库的覆盖能力，实现70%覆盖率的查询效率提升达4.03倍，并达到0.699的代理重建相似度。

Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection

少即是多：为生成器对齐的检索增强生成中的信息增益剪枝

Zhipeng Song, Yizhi Zhou, Xiangyu Kong, Jiulong Jiao, Xinrui Bao, Xu You, Xueqing Shi, Yuhang Zhou, Heng Qi

机构 * organization= School of Computer Science ； Technology, Dalian University of Technology , addressline= No.2 Linggong Road, Ganjingzi District , city= Dalian , postcode= 116024 , country= China ； organization= College of Health-Preservation ； Wellness, Dalian Medical University , addressline= No. 9 West Section of Lvshun South Road, Lvshunkou District , city= Dalian , postcode= 116044 , country= China ； organization= School of Information Engineering, Dalian Ocean University , addressline= No. 2-52, Heishijiao Street, Shahekou District , city= Dalian , postcode= 116023 , country= China ； organization= School of Information Engineering, Liaodong University , addressline= No.116 Linjiang Back Street, Zhenan District , city= Dandong , postcode= 118001 , country= China ； organization= Information Technology Center, Qinghai University , addressline= 251 Ningda Road, Chengbei District , city= Xining , postcode= 810016 , country= China ； organization= School of Electronic ； Information Engineering, Liaoning Technical University , addressline= 188 Longwan South Street, Sijiatun District , city= Huludao , postcode= 125105 , country= China ； organization= Tencent (Dalian Northern Interactive Entertainment Technology Co., Ltd.) , addressline= 21/F, Tencent Building, No. 26 Jingxian St, Ganjingzi District , city= Dalian , postcode= 116085 , country= China 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；retriever(abstract)；分类 cs.CL、cs.AI

AI总结 本文提出信息增益剪枝方法，通过生成器对齐的效用信号优化证据选择，提升RAG在有限上下文预算下的生成质量与效率。

Comments 26 pages, 10 figures

Optimizing Retrieval for RAG via Reinforcement Learning

通过强化学习优化RAG的检索

Jiawei Zhou, Lei Chen

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；retriever(abstract)；分类 cs.IR、cs.CL

AI总结 通过强化学习优化RAG检索，提升检索性能并适应多样化环境。

Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers

协作检索增强生成用于问答：通过对比层进行互信息交换和排序

Youmin Ko, Sungjong Seo, Hyunjoon Kim

机构 * Department of Artificial Intelligence, Hanyang University（人工智能学院，翰阳大学） ； Department of Data Science, Hanyang University（数据科学学院，翰阳大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL、cs.AI

AI总结 CoopRAG通过协作检索与生成机制，提升问答任务中检索与生成的准确性。

Comments Accepted to NeurIPS 2025

Beyond Component Strength: Synergistic Integration and Adaptive Calibration in Multi-Agent RAG Systems

超越组件强度：多智能体RAG系统中的协同整合与自适应校准

Jithin Krishnan

机构 * National University of Singapore（新加坡国立大学） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；hybrid retrieval(abstract)；分类 cs.CL、cs.AI

AI总结 该研究探讨了多智能体RAG系统中组件协同整合的重要性，发现通过混合检索、集合验证和自适应阈值等技术的协同作用，可显著降低退避率并减少幻觉，强调了标准化度量和自适应校准的必要性。

Comments 10 pages, 4 figures

Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems

Minseok Kim, Hankook Lee, Hyungjoon Koo

机构 * Sungkyunkwan University（成均馆大学） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；retriever(abstract)；分类 cs.IR、cs.AI

Comments 15 pages, 7 figures, 10 tables. To appear in the Proceedings of the 2025 Annual Computer Security Applications Conference (ACSAC)

A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation

Neal Gregory Lawton, Alfy Samuel, Anoop Kumar, Daben Liu

机构 * CapitalOne 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation

Ines Besrour, Jingbo He, Tobias Schreieder, Michael Färber

机构 * TU Dresden（德累斯顿理工大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments Accepted at CIKM 2025

Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation

Chaeyun Jang, Deukhwan Cho, Seanie Lee, Hyungi Lee, Juho Lee

机构 * KAIST（韩国科学技术院） ； Kookmin University（韩国釜山大学） 纠错

专题命中 检索器与排序 ：retrieval augmented generation(title,abstract)；retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.AI

Comments Accepted by NeurIPS 2025

Towards Reliable Retrieval in RAG Systems for Large Legal Datasets

Markus Reuter, Tobias Lingenberg, Rūta Liepiņa, Francesca Lagioia, Marco Lippi, Giovanni Sartor, Andrea Passerini, Burcu Sayin

机构 * Technical University of Darmstadt（德意志联邦共和国达姆斯塔特技术大学） ； University of Trento（特伦托大学） ； University of Florence（佛罗伦萨大学） ； University of Bologna（博洛尼亚大学） ； European University Institute（欧洲大学研究所） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；retriever(abstract)；分类 cs.IR、cs.CL

Comments Accepted for the 7th Natural Legal Language Processing Workshop (NLLP 2025), co-located with EMNLP 2025

Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented Generation

Minghao Tang, Shiyu Ni, Jiafeng Guo, Keping Bi

机构 * State Key Laboratory of AI Safety（人工智能安全国家重点实验室） ； Institute of Computing Technology（计算技术研究所） ； Chinese Academy of Sciences（中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.IR、cs.CL

Comments SIGIR-AP 2025

LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing

Yao Zhao, Yantian Ding, Zhiyue Zhang, Dapeng Yao, Yanxun Xu

机构 * Department of Applied Mathematics and Statistics（应用数学与统计学系） 纠错

专题命中 检索器与排序 ：retriever(title,abstract)；retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.AI

Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation

Vibhor Agrawal, Fay Wang, Rishi Puri

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；dense retrieval(abstract)；分类 cs.IR、cs.AI

Analise Semantica Automatizada com LLM e RAG para Bulas Farmaceuticas

Daniel Meireles do Rego

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；vector search(abstract)；分类 cs.IR、cs.CL

Comments in Portuguese language

Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control

Jinyan Su, Jennifer Healey, Preslav Nakov, Claire Cardie

机构 * Cornell University（康奈尔大学） ； Adobe Research（Adobe研究） ； Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed人工智能大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；knowledge retrieval(abstract)；分类 cs.IR、cs.AI

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection

San Kim, Jonghwi Kim, Yejin Jeon, Gary Geunbae Lee

机构 * Graduate School of Artificial Intelligence, POSTECH, Republic of Korea（人工智能研究生院，POSTECH，韩国） ； Department of Computer Science and Engineering, POSTECH, Republic of Korea（计算机科学与工程系，POSTECH，韩国） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；retriever(abstract)；分类 cs.CL、cs.AI

Comments 18 pages, accepted to ACL Findings 2025

Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

Deyu Zou, Yongqiang Chen, Mufei Li, Siqi Miao, Chenxi Liu, Bo Han, James Cheng, Pan Li

机构 * The Chinese University of Hong Kong（香港中文大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Hong Kong Baptist University（香港 Baptist大学） 纠错

专题命中 检索器与排序 ：retrieval augmented generation(title)；retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)

Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers

Chaitanya Sharma

机构 * Independent Researcher（独立研究者） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.IR、cs.CL

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models

Arjun Rao, Hanieh Alipour, Nick Pendar

机构 * SAP（SAP公司） 纠错

专题命中 检索器与排序 ：hybrid retrieval(title,abstract)；retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.AI

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis

Yi Jiang, Sendong Zhao, Jianbo Li, Haochun Wang, Bing Qin

机构 * Research Center for Social Computing and Interactive Robotics（社会计算与交互机器人研究中心） ； Harbin Institute of Technology（哈尔滨工业大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.IR、cs.AI

Comments Accepted by ACL 2025

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation

Guoxin Chen, Minpeng Liao, Peiying Yu, Dingmin Wang, Zile Qiao, Chao Yang, Xin Zhao, Kai Fan

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； Tongyi Lab（通义实验室） ； Soochow University（苏州大学） ； University of Oxford（牛津大学） ； Tsinghua University（清华大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL、cs.AI

Comments Camera ready version for ICML 2025

DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation

Jiashuo Sun, Xianrui Zhong, Sizhe Zhou, Jiawei Han

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

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；knowledge retrieval(abstract)；分类 cs.CL、cs.AI

Comments 24 pages, 7 figures, 15 tables

KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models

Weijie Chen, Ting Bai, Jinbo Su, Jian Luan, Wei Liu, Chuan Shi

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； University of Science and Technology Beijing（北京科技大学） ； Xiaomi Corporation（小米公司） 纠错

专题命中 检索器与排序 ：retriever(title,abstract)；retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.AI

The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation

Zheng Zhang, Ning Li, Qi Liu, Rui Li, Weibo Gao, Qingyang Mao, Zhenya Huang, Baosheng Yu, Dacheng Tao

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） ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL、cs.AI

Comments 12 pages

HeteRAG: A Heterogeneous Retrieval-augmented Generation Framework with Decoupled Knowledge Representations

Peiru Yang, Xintian Li, Zhiyang Hu, Jiapeng Wang, Jinhua Yin, Huili Wang, Lizhi He, Shuai Yang, Shangguang Wang, Yongfeng Huang, Tao Qi

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.AI

Comments 10 pages, 5 figures

Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation

Teng Shi, Jun Xu, Xiao Zhang, Xiaoxue Zang, Kai Zheng, Yang Song, Han Li

专题命中 检索器与排序 ：retrieval augmented generation(title)；retrieval-augmented generation(abstract)；RAG(abstract)；retriever(abstract)

Comments Accepted by SIGIR 2025

OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning

Jiawei Zhou, Lei Chen

专题命中 检索器与排序 ：RAG(title,abstract)；retrieval-augmented generation(abstract)；retriever(abstract)；分类 cs.IR、cs.CL

LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation

Haitao Li, Yifan Chen, Yiran Hu, Qingyao Ai, Junjie Chen, Xiaoyu Yang, Jianhui Yang, Yueyue Wu, Zeyang Liu, Yiqun Liu

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；knowledge retrieval(abstract)；分类 cs.IR、cs.CL

Comments 10 pages

Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation

Shubham Agarwal, Sai Sundaresan, Subrata Mitra, Debabrata Mahapatra, Archit Gupta, Rounak Sharma, Nirmal Joshua Kapu, Tong Yu, Shiv Saini

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；retriever(abstract)；分类 cs.CL、cs.AI

Comments Accepted at SIGMOD 2025

Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation

Rubing Chen, Xulu Zhang, Jiaxin Wu, Wenqi Fan, Xiao-Yong Wei, Qing Li

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；knowledge retrieval(abstract)；分类 cs.CL、cs.AI