RAG / 检索增强生成

Agentic AI-Driven Technical Troubleshooting for Enterprise Systems: A Novel Weighted Retrieval-Augmented Generation Paradigm

Rajat Khanda

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

Hybrid RAG-empowered Multi-modal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-based Contract Approach

Cheng Su, Jinbo Wen, Jiawen Kang, Yonghua Wang, Yuanjia Su, Hudan Pan, Zishao Zhong, M. Shamim Hossain

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

Comments 13 pages, 7 figures

Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation

Ziwei Liu, Liang Zhang, Qian Li, Jianghua Wu, Guangxu Zhu

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

Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data

Anum Afzal, Juraj Vladika, Gentrit Fazlija, Andrei Staradubets, Florian Matthes

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

Toward Optimal Search and Retrieval for RAG

Alexandria Leto, Cecilia Aguerrebere, Ishwar Bhati, Ted Willke, Mariano Tepper, Vy Ai Vo

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

Comments Accepted to NeurIPS 2024 Workshop ATTRIB

TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network

Nouf Alabbasi, Omar Erak, Omar Alhussein, Ismail Lotfi, Sami Muhaidat, Merouane Debbah

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

SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation

Minda Hu, Licheng Zong, Hongru Wang, Jingyan Zhou, Jingjing Li, Yichen Gao, Kam-Fai Wong, Yu Li, Irwin King

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

Comments This work has been accepted by EMNLP 2024

AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task

Herbert Ullrich, Tomáš Mlynář, Jan Drchal

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

Question-Based Retrieval using Atomic Units for Enterprise RAG

Vatsal Raina, Mark Gales

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

Comments 14 pages, 5 figures, 5 tables

TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems

Xinke Jiang, Yue Fang, Rihong Qiu, Haoyu Zhang, Yongxin Xu, Hao Chen, Wentao Zhang, Ruizhe Zhang, Yuchen Fang, Xu Chu, Junfeng Zhao, Yasha Wang

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

Comments version 1.0

LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation

Keheng Wang, Feiyu Duan, Peiguang Li, Sirui Wang, Xunliang Cai

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

Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology

Shashi Kant Gupta, Aditya Basu, Bradley Taylor, Anai Kothari, Hrituraj Singh

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

Comments 18 pages

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela

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

Comments Accepted at NeurIPS 2020

Forecasting Bacterial Antimicrobial Resistance Trends Using Machine Learning on WHO GLASS Surveillance Data: A Retrieval-Augmented Generation Approach for Policy Decision Support

基于机器学习对WHO GLASS监测数据的细菌抗菌药物耐药趋势预测：一种用于政策决策支持的检索增强生成方法

Md Tanvir Hasan Turja

机构 * Independent Researcher（独立研究者） ； London, United Kingdom（伦敦，英国） 纠错

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

AI总结 利用XGBoost模型预测全球抗菌药物耐药趋势，结合检索增强生成系统提供可溯源的政策建议，误差较基线降低85.3%。

Comments 20 pages, 8 figures, code and data available at https://github.com/TanvirTurja/amr-forecasting-rag

CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG

CARROT：一种用于RAG的学得式成本约束检索优化系统

Ziting Wang, Haitao Yuan, Wei Dong, Gao Cong, Feifei Li

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

AI总结 CARROT通过MCTS和配置代理优化RAG检索，提升检索效率与准确性，实验显示性能提升达30%。

Comments Accepted to ICDE 2026. Updated title (previously "CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation")

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation

Ali Naseh, Yuefeng Peng, Anshuman Suri, Harsh Chaudhari, Alina Oprea, Amir Houmansadr

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） ； Northeastern University（东北大学） 纠错

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

Comments This is the full version (27 pages) of the paper 'Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation' published at CCS 2025

Automated Literature Review Using NLP Techniques and LLM-Based Retrieval-Augmented Generation

Nurshat Fateh Ali, Md. Mahdi Mohtasim, Shakil Mosharrof, T. Gopi Krishna

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

Comments Key Words : T5, SpaCy, Large Language Model, GPT, ROUGE, Literature Review, Natural Language Processing, Retrieval-augmented generation

The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs

Mert Yazan, Suzan Verberne, Frederik Situmeang

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

Comments Accepted to the IR-RAG Workshop at SIGIR 2024

Retrieval-Augmented Generation for AI-Generated Content: A Survey

Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, Bin Cui

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

Comments Citing 353 papers, 22 pages, 1 table, 12 figures. Project: https://github.com/PKU-DAIR/RAG-Survey

Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class Imbalance

在极端类别不平衡下基于网络的提示工程对抗有组织的Astroturf活动

Nikos Kanakaris, Heng Ping, Xiongye Xiao, Nesreen K. Ahmed, Luca Luceri, Emilio Ferrara, Paul Bogdan

机构 * University of Southern California（美国南加州大学） ； Cisco AI Research（思科人工智能研究） 纠错

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

AI总结 本文提出基于大型语言模型的Balanced RAG框架，通过提示工程和平衡检索增强生成技术，在极端类别不平衡下有效识别协调虚假信息活动。

Journal ref WWW '25: Companion Proceedings of the ACM on Web Conference 2025

Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval

诊断与缓解智能体说服中的复合失败：基于分类策略检索

Sana Ayromlou, Purvi Sehgal, Pradyumna Narayana

机构 * Google（谷歌） 纠错

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

AI总结 针对智能体在主观任务中因语义泄露导致的复合错误，提出分类策略RAG（TS-RAG），通过离散类别瓶颈解耦论证结构与主题内容，显著提升抽象逻辑迁移能力，并在非对称部署中增强轻量级说服者性能。

Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge

检索记忆中的时间有效性：消除AI智能体在知识演化中的过时事实错误

Neeraj Yadav

机构 * MemStrata.dev — Called It Inc. (Enterprise)（MemStrata.dev — Called It Inc.（企业）） 纠错

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

AI总结 针对RAG无法处理知识演化导致过时事实错误的问题，提出MemStrata，通过确定性替换规则维护时间有效性，在演化知识上准确率达0.95-1.00，过时事实错误率降至~0%。

Comments 21 pages, 5 tables. Code, prompts, and evaluation datasets included

Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval

认知偏见注入：通过选择性上下文检索操纵LLM观点

Hao Wu, Prateek Saxena

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(summary_cn,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI、cs.DB

AI总结 研究通过检索增强生成（RAG）数据库注入事实正确但认知偏见的段落，以操纵LLM输出立场，并提出基于几何度量的攻击与防御方法BiasDef。

PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality

PeerCheck: 提升大语言模型生成的学术评审至人类水平质量

Zeyuan Chen, Ziqing Yang, Yihan Ma, Michael Backes, Yang Zhang

机构 * CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心） 纠错

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

AI总结 提出PeerCheck框架，分析LLM与人类评审差异，采用思维链和检索增强生成提升评审质量，发现思维链显著改善但RAG存在悖论。

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

结合检索增强文本生成与大型语言模型的阅读内容推荐

Sooyeon Kim, Piotr S. Maciąg

机构 * Institute of Computer Science, Warsaw University of Technology（计算机科学学院，华沙技术大学） 纠错

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

AI总结 提出结合检索增强生成（RAG）与大型语言模型的系统，通过四个模块实现个性化阅读内容生成，实验表明RAG将相关性和接地性提升26-35个百分点。

TimeLens: On-Device Artifact Recognition with Retrieval-Augmented Question Answering for the Grand Egyptian Museum

TimeLens: 面向大埃及博物馆的基于检索增强问答的设备端文物识别

Rawan Hesham, Ali Ashraf, Amr Ahmed, Malak Alaa, Omar Ahmed, Omar Wagih

机构 * Grand Egyptian Museum（大埃及博物馆） 纠错

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

AI总结 针对博物馆场景中的细粒度视觉相似性、训练数据与手持相机差距以及AI幻觉问题，提出设备端文物检测器与双语检索增强生成（RAG）问答系统，实现实时识别与可靠问答。

Comments 6 pages, 4 figures, 5 tables. Submitted to AIVRCH 2026

Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations

注意差距：用LLM弥合多垂直领域推荐中的行为孤岛

Nimesh Sinha, Raghav Saboo, Martin Wang, Sudeep Das

机构 * DoorDash Inc.（DoorDash公司） 纠错

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

AI总结 提出利用LLM从数据丰富垂直领域（如餐厅）向稀疏领域（如杂货）迁移知识的框架，通过分层RAG生成多级特征，集成到MTL排序模型，显著提升新兴业务个性化与参与度。

Inference Cost Attacks for Retrieval-Augmented Large Language Models

检索增强型大语言模型的推理成本攻击

Chengliang Liu, Liangbo Ning, Yujuan Ding, Wenqi Fan

机构 * The Hong Kong Polytechnic University（香港理工大学） 纠错

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

AI总结 提出RA-ICA攻击范式，通过向外部知识库注入恶意文档，利用CREEP框架和MA-GRPO算法，使RAG增强的LLM系统推理时token消耗增加高达13.12倍且成功率超过90%。

Comments Accepted at The ACM Web Conference 2026 (WWW '26)

Journal ref Proceedings of the ACM Web Conference 2026 (WWW '26), April 13-17, 2026, Dubai, United Arab Emirates

TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation

TCAR-Gen: 基于证据融合的时间图检索用于知识增强生成

Sidra Nasir, Muhammad Noman Zahid, Rizwan Ahmed Khan

机构 * Dipartimento di Informatica, Università di Verona（威尼斯大学计算机科学系） ； School of Advanced Studies, University of Camerino（坎皮诺大学高级研究学院） ； Department of Computer Science, School of Mathematics and Computer Science, Institute of Business Administration (IBA), Karachi, Pakistan（卡拉奇工商管理学院（IBA）数学与计算机科学学院计算机科学系） 纠错

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

AI总结 提出TCAR-Gen框架，结合查询条件图神经网络、时间证据融合和树链推理，在历史犯罪叙事问答中实现时间推理和多源证据融合，优于现有RAG方法。

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval

DynaTree: 面向时效性新闻检索的动态智能检索树

Siyuan Qi, Xinyuan Wang, Yingxuan Yang, Haochuan Guo, Jianghao Lin, Weiwen Liu, Yong Yu, Weinan Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

AI总结 提出DynaTree两阶段框架，通过离线构建可复用检索树和在线轻量子树选择，实现高效、自适应的时效性新闻检索，在Syft新闻基准和BEIR数据集上优于标准RAG和现有智能体方法。