RAG / 检索增强生成 - arXivDaily 专题

2504.01281 2025-05-21 cs.LG cs.AI cs.CL cs.IR 85%

Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding

Sakhinana Sagar Srinivas, Akash Das, Shivam Gupta, Venkataramana Runkana

机构 * Tata Research Development（塔塔研究与发展中心）； Design Center, Bangalore（班加罗尔设计中心）

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

2505.00443 2025-05-02 cs.DC 85%

Distributed Retrieval-Augmented Generation

Chenhao Xu, Longxiang Gao, Yuan Miao, Xi Zheng

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

2504.19754 2025-04-29 cs.IR cs.AI cs.CL 85%

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

Carlo Merola, Jaspinder Singh

机构 * Department of Computer Science and Engineering, University of Bologna（计算机科学与工程系，博洛尼亚大学）

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 13 pages, 2 figures, Second Workshop on Knowledge-Enhanced Information Retrieval, ECIR 2025

2504.14917 2025-04-22 cs.LG 85%

POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications

Chunjing Gan, Dan Yang, Binbin Hu, Ziqi Liu, Yue Shen, Zhiqiang Zhang, Jian Wang, Jun Zhou

机构 * Ant Group（蚂蚁集团）

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

2504.09795 2025-04-15 cs.CL cs.AI cs.CV cs.IR 85%

VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents

Ryota Tanaka, Taichi Iki, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Jun Suzuki

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 Accepted by CVPR 2025; project page: https://vdocrag.github.io

2504.08744 2025-04-15 cs.IR cs.AI cs.CL 85%

ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responses

Esmail Gumaan

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

Comments 30 pages, 4 figures

2504.08745 2025-04-15 cs.IR cs.AI cs.CL 85%

Improving RAG for Personalization with Author Features and Contrastive Examples

Mert Yazan, Suzan Verberne, Frederik Situmeang

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

2410.00004 2025-03-27 cs.IR cs.AI cs.CL 85%

Retro-li: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization

Gentiana Rashiti, Geethan Karunaratne, Mrinmaya Sachan, Abu Sebastian, Abbas Rahimi

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

Journal ref Published in: Proceedings of 27TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, IOS Press, 392, 2024, pp. 2974 - 2982

2503.14649 2025-03-24 cs.IR cs.AI cs.CL cs.DC 85%

RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving

Wenqi Jiang, Suvinay Subramanian, Cat Graves, Gustavo Alonso, Amir Yazdanbakhsh, Vidushi Dadu

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 16 pages, 19 figures, 4 tables

2503.16071 2025-03-21 cs.CL cs.AI cs.IR 85%

Tuning LLMs by RAG Principles: Towards LLM-native Memory

Jiale Wei, Shuchi Wu, Ruochen Liu, Xiang Ying, Jingbo Shang, Fangbo Tao

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

2503.10654 2025-03-17 cs.CL cs.AI cs.IR 85%

Improving RAG Retrieval via Propositional Content Extraction: a Speech Act Theory Approach

João Alberto de Oliveira Lima

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

Comments 19 pages, 4 figures

2410.18141 2025-03-11 cs.IR cs.AI cs.CL 85%

SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback

Jingsheng Gao, Linxu Li, Weiyuan Li, Yuzhuo Fu, Bin Dai

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

2503.04973 2025-03-10 cs.CL cs.AI cs.IR cs.LG 85%

Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning

Giulio Corallo, Orion Weller, Fabio Petroni, Paolo Papotti

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

2503.01859 2025-03-05 cs.CL cs.AI cs.IR 85%

Optimizing Retrieval-Augmented Generation of Medical Content for Spaced Repetition Learning

Jeremi I. Kaczmarek, Jakub Pokrywka, Krzysztof Biedalak, Grzegorz Kurzyp, Łukasz Grzybowski

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

2406.00944 2025-03-03 cs.CL cs.AI cs.IR 85%

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation

Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng

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 ICLR 2025

2410.09662 2025-02-25 cs.SE 85%

Evaluating the Effectiveness and Efficiency of Demonstration Retrievers in RAG for Coding Tasks

Pengfei He, Shaowei Wang, Shaiful Chowdhury, Tse-Hsun Chen

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

Comments 11 pages, 6 figures, 6 tables, accepted by SANER 2025

2502.15701 2025-02-25 cs.IR cs.AI cs.CL 85%

Political Events using RAG with LLMs

Muhammad Arslan, Saba Munawar, Christophe Cruz

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

2502.15700 2025-02-25 cs.IR cs.AI cs.CL 85%

Sustainable Digitalization of Business with Multi-Agent RAG and LLM

Muhammad Arslan, Saba Munawar, Christophe Cruz

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

2501.16075 2025-01-28 cs.CL cs.AI cs.IR 85%

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation

Maxime Louis, Hervé Déjean, Stéphane Clinchant

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

2410.17952 2025-01-28 cs.CL cs.AI cs.IR cs.LG 85%

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains

Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C. Ho, Carl Yang, Qi He

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 Accepted to NAACL 2025 main conference

Journal ref NAACL 2025

2501.13993 2025-01-27 cs.CL cs.AI cs.IR 85%

CAPRAG: A Large Language Model Solution for Customer Service and Automatic Reporting using Vector and Graph Retrieval-Augmented Generation

Hamza Landolsi, Kais Letaief, Nizar Taghouti, Ines Abdeljaoued-Tej

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 14 pages, 5 Figures, 3 Tables

2406.14162 2025-01-24 cs.IR cs.AI cs.CL 85%

DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation

Jingwei Ni, Tobias Schimanski, Meihong Lin, Mrinmaya Sachan, Elliott Ash, Markus Leippold

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 NAACL 2025 Long

2412.15246 2024-12-23 cs.CL cs.AI cs.AR cs.DC cs.IR 85%

Accelerating Retrieval-Augmented Generation

Derrick Quinn, Mohammad Nouri, Neel Patel, John Salihu, Alireza Salemi, Sukhan Lee, Hamed Zamani, Mohammad Alian

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

2411.02832 2024-11-07 cs.CL cs.AI cs.IR 85%

PersianRAG: A Retrieval-Augmented Generation System for Persian Language

Hossein Hosseini, Mohammad Sobhan Zare, Amir Hossein Mohammadi, Arefeh Kazemi, Zahra Zojaji, Mohammad Ali Nematbakhsh

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

2406.13249 2024-10-31 cs.CL cs.AI cs.IR 85%

R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation

Fuda Ye, Shuangyin Li, Yongqi Zhang, Lei Chen

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 Accepted to EMNLP 2024 Findings

2410.14479 2024-10-21 cs.CR cs.LG 85%

Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models

Cody Clop, Yannick Teglia

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

Comments 12 pages, 5 figures

2410.09584 2024-10-15 cs.CL cs.AI cs.IR cs.LG 85%

Toward General Instruction-Following Alignment for Retrieval-Augmented Generation

Guanting Dong, Xiaoshuai Song, Yutao Zhu, Runqi Qiao, Zhicheng Dou, Ji-Rong Wen

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 Working in progress

2405.18727 2024-10-07 cs.CL cs.AI cs.IR 85%

CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control

Huanshuo Liu, Hao Zhang, Zhijiang Guo, Jing Wang, Kuicai Dong, Xiangyang Li, Yi Quan Lee, Cong Zhang, Yong Liu

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 29 pages, 10 figures, 11 tables

2409.13707 2024-09-24 cs.IR cs.AI cs.CL 85%

Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support

Paulina Toro Isaza, Michael Nidd, Noah Zheutlin, Jae-wook Ahn, Chidansh Amitkumar Bhatt, Yu Deng, Ruchi Mahindru, Martin Franz, Hans Florian, Salim Roukos

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 7 pages, 3 figures, 6 tables

2408.08921 2024-09-11 cs.AI cs.CL cs.IR 85%

Graph Retrieval-Augmented Generation: A Survey

Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, Siliang Tang

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 Ongoing work. Compared to the first version, several references have been added and a GitHub repository link has been provided

1. 检索器与排序 4528 篇

Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding

Distributed Retrieval-Augmented Generation

Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation

POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications

VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents

ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responses

Improving RAG for Personalization with Author Features and Contrastive Examples

Retro-li: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization

RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving

Tuning LLMs by RAG Principles: Towards LLM-native Memory

Improving RAG Retrieval via Propositional Content Extraction: a Speech Act Theory Approach

SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback

Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning

Optimizing Retrieval-Augmented Generation of Medical Content for Spaced Repetition Learning

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation

Evaluating the Effectiveness and Efficiency of Demonstration Retrievers in RAG for Coding Tasks

Political Events using RAG with LLMs

Sustainable Digitalization of Business with Multi-Agent RAG and LLM

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains

CAPRAG: A Large Language Model Solution for Customer Service and Automatic Reporting using Vector and Graph Retrieval-Augmented Generation

DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation

Accelerating Retrieval-Augmented Generation

PersianRAG: A Retrieval-Augmented Generation System for Persian Language

R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation

Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models

Toward General Instruction-Following Alignment for Retrieval-Augmented Generation

CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control

Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support

Graph Retrieval-Augmented Generation: A Survey