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 4558 信号源:cs.IR, cs.CL, cs.AI, cs.DB

1. 检索器与排序 4558 篇

2312.07559 2023-12-18 cs.CL cs.AI cs.LG 73%

PaperQA: Retrieval-Augmented Generative Agent for Scientific Research

Jakub Lála, Odhran O'Donoghue, Aleksandar Shtedritski, Sam Cox, Samuel G. Rodriques, Andrew D. White

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.01429 2023-10-04 cs.CL cs.AI 73%

Chatmap : Large Language Model Interaction with Cartographic Data

Eren Unlu

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

Comments 9 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.12847 2023-01-31 cs.IR cs.CL 73%

Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks

Antoine Louis, Gijs van Dijck, Gerasimos Spanakis

专题命中 检索器与排序 :retriever(abstract);dense retrieval(abstract);分类 cs.IR、cs.CL

Comments EACL 2023. Code is available at https://github.com/maastrichtlawtech/gdsr

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.02401 2023-01-09 cs.CL cs.AI 73%

You Truly Understand What I Need: Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona

Jungwoo Lim, Myunghoon Kang, Yuna Hur, Seungwon Jung, Jinsung Kim, Yoonna Jang, Dongyub Lee, Hyesung Ji, Donghoon Shin, Seungryong Kim, Heuiseok Lim

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

Comments Accepted at Findings of EMNLP 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.13678 2022-10-26 cs.CL cs.IR cs.LG 73%

Bridging the Training-Inference Gap for Dense Phrase Retrieval

Gyuwan Kim, Jinhyuk Lee, Barlas Oguz, Wenhan Xiong, Yizhe Zhang, Yashar Mehdad, William Yang Wang

专题命中 检索器与排序 :retriever(abstract);dense retrieval(abstract);分类 cs.IR、cs.CL

Comments Findings of EMNLP 2022; 12 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.12887 2022-10-25 cs.CL cs.AI 73%

Retrieval Augmentation for Commonsense Reasoning: A Unified Approach

Wenhao Yu, Chenguang Zhu, Zhihan Zhang, Shuohang Wang, Zhuosheng Zhang, Yuwei Fang, Meng Jiang

专题命中 检索器与排序 :retriever(abstract);knowledge retrieval(abstract);分类 cs.CL、cs.AI

Comments EMNLP 2022 (main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2104.10129 2021-04-21 cs.CL cs.IR 73%

Efficient Retrieval Optimized Multi-task Learning

Hengxin Fun, Sunil Gandhi, Sujith Ravi

专题命中 检索器与排序 :retriever(abstract);knowledge retrieval(abstract);分类 cs.IR、cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.01280 2025-08-26 cs.IR cs.MM 72%

Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG

Aleksander Theo Strand, Sushant Gautam, Cise Midoglu, Pål Halvorsen

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

Comments accepted to CBMI 2024 as a demonstration; https://github.com/simula/soccer-rag. arXiv admin note: text overlap with arXiv:2406.01273

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.03970 2025-05-08 cs.CL 72%

A Reasoning-Focused Legal Retrieval Benchmark

Lucia Zheng, Neel Guha, Javokhir Arifov, Sarah Zhang, Michal Skreta, Christopher D. Manning, Peter Henderson, Daniel E. Ho

机构 * Stanford University(斯坦福大学) Princeton University(普林斯顿大学)

专题命中 检索器与排序 :RAG(abstract,comments);retriever(abstract);分类 cs.CL

Comments CS&Law 2025. For data, see https://reglab.github.io/legal-rag-benchmarks/

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.15809 2026-07-20 eess.SY cs.SY 新提交 71%

From Similarity to Feasibility: Diffusion-Refined Retrieval-Augmented Generation for Distribution Network Optimization

从相似性到可行性:用于配电网优化的扩散细化检索增强生成

Yuxuan Chen, Haipeng Xie, Shuo Dai, Ruoyi Xu, Zhaohong Bie

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

AI总结 针对配电网优化中传统方法的不足,提出GridRAG框架,通过将场景特征与最优解嵌入联合空间,检索相似历史场景,并用扩散模块细化解,实现跨场景通用且加速求解,相比基线有显著优势。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.19224 2026-06-30 cs.SE 71%

iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation

iCoRe: 一种迭代相关性感知的Bug重现测试生成检索器

Junyi Wang, Jialun Cao, Zhongxin Liu

专题命中 检索器与排序 :retriever(title)

AI总结 本文提出iCoRe,一种迭代相关性感知的Bug重现测试生成检索器,通过区分源代码与测试用例的检索需求、结合文本语义与函数调用结构、以及实现检索与生成阶段的反馈循环,提升Bug重现测试生成的准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.17430 2026-06-17 cs.CV 新提交 71%

CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented Generation

CIAN:基于检索增强生成的事件丰富图像描述的多阶段框架

Trinh Thi Thu Hien, Trung-Nghia Le

机构 * University of Science, Ho Chi Minh City(胡志明市理科大学) Vietnam National University, Ho Chi Minh City(越南国家大学胡志明市分校)

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

AI总结 提出多阶段框架CIAN,通过检索相关文章并利用LoRA微调Qwen模型生成叙事,结合N-Gram精炼,在OpenEvents-V1上提升CIDEr从0.030到0.094,实现事件丰富的图像描述。

Comments SOICT 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.03833 2026-04-07 cs.CV 71%

SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning

SPARK-IL:基于频谱检索的增强型RAG用于通过增量学习的知识驱动深度伪造检测

Hessen Bougueffa Eutamene, Abdellah Zakaria Sellam, Abdelmalik Taleb-Ahmed, Abdenour Hadid

机构 * Univ. Polytechnique Hauts-de-France(上法兰西理工大学) Institute of Applied Sciences and Intelligent Systems – Lecce(应用科学与智能系统研究所(莱切)) Department of Innovation Engineering, University of Salento(萨伦托大学创新工程系) Sorbonne Center for Artificial Intelligence, Sorbonne University Abu Dhabi(索邦大学阿布扎比分校索邦人工智能中心)

专题命中 检索器与排序 :RAG(title)

AI总结 本文提出SPARK-IL框架,结合双路径频谱分析与增量学习,利用冻结的ViT-L/14编码器生成语义表示,并通过频谱嵌入融合与残差连接实现跨生成器检测,达到94.6%的准确率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.07302 2025-08-13 eess.AS 71%

XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation

Tianlun Zuo, Jingbin Hu, Yuke Li, Xinfa Zhu, Hai Li, Ying Yan, Junhui Liu, Danming Xie, Lei Xie

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

Comments Accepted by ASRU 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.12558 2025-07-25 cs.SE 71%

When Retriever Meets Generator: A Joint Model for Code Comment Generation

Tien P. T. Le, Anh M. T. Bui, Huy N. D. Pham, Alessio Bucaioni, Phuong T. Nguyen

专题命中 检索器与排序 :retriever(title)

Comments The paper has been peer-reviewed and accepted for publication in the proceedings of the 19th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.02275 2025-01-07 q-bio.QM 71%

Genomic and pathological analyses of an asymmetric true hermaphroditism case in a female labrador retriever

Yihang Zhou

专题命中 检索器与排序 :retriever(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.03122 2024-10-16 cs.NI 71%

Automatic Retrieval-augmented Generation of 6G Network Specifications for Use Cases

Yun Tang, Weisi Guo

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

Comments 7 pages, 6 figures, Submitted to IEEE Comm Magazine for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.05855 2024-08-13 cs.CR cs.LG 71%

Using Retriever Augmented Large Language Models for Attack Graph Generation

Renascence Tarafder Prapty, Ashish Kundu, Arun Iyengar

专题命中 检索器与排序 :retriever(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.10384 2023-12-29 cs.SD eess.AS 71%

Retrieval Augmented Generation of Symbolic Music with LLMs

Nicolas Jonason, Luca Casini, Carl Thomé, Bob L. T. Sturm

专题命中 检索器与排序 :retrieval augmented generation(title)

Comments LBD @ ISMIR 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.05261 2023-11-10 cs.CR 71%

RAGLog: Log Anomaly Detection using Retrieval Augmented Generation

Jonathan Pan, Swee Liang Wong, Yidi Yuan

专题命中 检索器与排序 :retrieval augmented generation(title)

Comments arXiv admin note: substantial text overlap with arXiv:2203.10960

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.04310 2023-11-09 cs.HC 71%

KNIMEZoBot: Enhancing Literature Review with Zotero and KNIME OpenAI Integration using Retrieval-Augmented Generation

Suad Alshammari, Lama Basalelah, Walaa Abu Rukbah, Ali Alsuhibani, Dayanjan S. Wijesinghe

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2211.02608 2022-11-07 cs.OH 71%

Knowledge Retrieval With Functional Object-Oriented Networks

Shawn Diaz

专题命中 检索器与排序 :knowledge retrieval(title)

Comments 3 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05564 2026-08-20 cs.CL 70%

THIVLVC: Retrieval Augmented Dependency Parsing for Latin

THIVLVC:用于拉丁语的检索增强依存解析

Luc Pommeret, Thibault Wagret, Jules Deret

机构 * Université Paris-Saclay, CNRS, LISN(巴黎-萨克雷大学,法国国家科学研究中心,语言与语音处理实验室) École Normale Supérieure de Lyon, HISOMA(里昂高等师范学院,历史与古代地中海文明研究所)

专题命中 检索器与排序 :RAG(abstract,abstract_cn);分类 cs.CL

AI总结 THIVLVC通过检索相似结构条目并利用大语言模型优化,提升了拉丁语依存解析的CLAS得分,尤其在诗歌部分表现更优。

Journal ref Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.15698 2026-08-18 cs.CV cs.IR 新提交 70%

ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval

ConceptFormer:学习自适应潜在概念以实现视觉文档检索中的查询-文档对齐

Peng Chunyi, Xu Zhipeng, Yan Yukun, Liu Zhenghao, Yu Shi, Mei Sen, Sun Yubo, Zhang Yongheng, Zhou Jie, Gu Yu, Yu Ge, Sun Maosong

机构 * Northeastern University(东北大学) Tsinghua University(清华大学) Peking University(北京大学)

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

AI总结 针对视觉文档检索中现有监督信号的局限,本文提出ConceptFormer框架,以自适应潜在概念为中间表示衔接语义鸿沟,在基准测试中较最强基线实现了16.7%、22.1%的NDCG@10相对提升,性能优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.08055 2026-08-11 cs.AI 新提交 70%

SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents

SodaMem:面向大语言模型智能体的基于证据的时序图记忆

Fengrong Wan, Chengcan Wu, Ningtao Lyu

专题命中 检索器与排序 :RAG(abstract,abstract_cn);分类 cs.AI

AI总结 针对LLM智能体对话的时效性、来源追溯等问题,提出基于证据的时序图记忆SodaMem,在LongMemEval-S上以Flash级花费达到高准确率,性能优于部分高成本系统。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16406 2026-08-11 cs.CR cs.CL 版本更新 70%

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models

检索增强防御:针对大语言模型的自适应且可控制的越狱防范

Guangyu Yang, Jinghong Chen, Jingbiao Mei, Weizhe Lin, Bill Byrne

机构 * Department of Engineering University of Cambridge(工程系剑桥大学)

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

AI总结 针对大语言模型越狱攻击的挑战,提出检索增强防御(RAD)框架,在StrongREJECT数据集上验证其可降低强力越狱攻击有效性,同时平衡安全性与实用性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.02112 2026-08-04 cs.LG cs.IR 新提交 70%

Do Static Embeddings Add Value to Hybrid Dutch Retrieval?

静态嵌入是否为混合荷兰语检索增加价值?

António Pereira Barata

专题命中 检索器与排序 :retriever(abstract);hybrid retrieval(abstract);分类 cs.IR

AI总结 本研究针对荷兰语检索任务开展受控评估,发现静态嵌入无法为混合检索增加价值,双检索器的词汇-Transformer架构是可靠默认方案。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00558 2026-08-04 cs.SE cs.AI 新提交 70%

AiFlow: Token-Native Reactive Orchestration with Bounded Backpressure for Streaming LLM Applications

AiFlow:面向流式大语言模型应用的带界背压令牌原生反应式编排框架

Qunhui Zhang

专题命中 检索器与排序 :RAG(abstract,abstract_cn);分类 cs.AI

AI总结 针对现有流式LLM工作流编排的背压等管理缺陷,提出AiFlow令牌原生反应式编排模型,经实验验证可降低应用TTFPT并控制队列深度。

Comments 24 pages, 5 figures, 12 tables, 1 algorithm, and 1 code listing. Public implementation: https://github.com/ModelEngine-Group/fit-framework

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.27136 2026-07-30 cs.IR 新提交 70%

KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval

KAMR:基于知识对齐多跳检索的接地生成

Xiaochen Wang, Yuan Zhong, Haoyu Wang, Ting Wang, Fenglong Ma

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

AI总结 该研究针对多跳检索中三元组排序与监督缺失问题,提出KAMR知识对齐多跳检索器,通过构建部分对齐数据集优化对比目标,在多基准与LLM主干上提升了多跳检索和下游问答性能。

Comments Accepted by COLM'26

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14802 2026-07-28 cs.IR 版本更新 70%

Graph-Based Re-ranking in Information Retrieval and Beyond: A Survey

信息检索及其他领域中基于图的重排:一项综述

Md Shahir Zaoad, Niamat Zawad, Priyanka Ranade, Latifur Khan

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

AI总结 综述基于图的信息检索重排方法,介绍其在相关AI范式中的作用,通过引入分类法和时间线深入回顾该范式,分析实验情况,最后基于挑战与机遇给出未来研究建议。

Comments This is an extended version of the previous release (V1)

详情

展开后加载摘要…

URL PDF HTML 收藏