RAG / 检索增强生成 - arXivDaily 专题

2412.13018 2025-02-18 cs.CL 83%

OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain

Shuting Wang, Jiejun Tan, Zhicheng Dou, Ji-Rong Wen

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

2502.09073 2025-02-14 cs.CL 83%

Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables

Xuzhao Geng, Haozhao Wang, Jun Wang, Wei Liu, Ruixuan Li

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

2501.14733 2025-01-28 cs.DC cs.AI 83%

LLM as HPC Expert: Extending RAG Architecture for HPC Data

Yusuke Miyashita, Patrick Kin Man Tung, Johan Barthélemy

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.AI

Comments preprint

2409.12941 2025-01-28 cs.CL 83%

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Satyapriya Krishna, Kalpesh Krishna, Anhad Mohananey, Steven Schwarcz, Adam Stambler, Shyam Upadhyay, Manaal Faruqui

专题命中 RAG评测：retrieval-augmented generation(title,abstract)；RAG(abstract)；分类 cs.CL

Comments Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025

2410.11414 2025-01-22 cs.CL 83%

ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

Zhongxiang Sun, Xiaoxue Zang, Kai Zheng, Yang Song, Jun Xu, Xiao Zhang, Weijie Yu, Yang Song, Han Li

专题命中 RAG评测：retrieval-augmented generation(title,abstract)；RAG(abstract)；分类 cs.CL

Comments 23pages

2412.14457 2024-12-20 cs.IR 83%

VISA: Retrieval Augmented Generation with Visual Source Attribution

Xueguang Ma, Shengyao Zhuang, Bevan Koopman, Guido Zuccon, Wenhu Chen, Jimmy Lin

专题命中 RAG评测：retrieval augmented generation(title)；retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.IR

2410.03845 2024-12-03 cs.CL cs.AR 83%

ORAssistant: A Custom RAG-based Conversational Assistant for OpenROAD

Aviral Kaintura, Palaniappan R, Shui Song Luar, Indira Iyer Almeida

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

2406.04744 2024-11-04 cs.CL 83%

CRAG -- Comprehensive RAG Benchmark

Xiao Yang, Kai Sun, Hao Xin, Yushi Sun, Nikita Bhalla, Xiangsen Chen, Sajal Choudhary, Rongze Daniel Gui, Ziran Will Jiang, Ziyu Jiang, Lingkun Kong, Brian Moran, Jiaqi Wang, Yifan Ethan Xu, An Yan, Chenyu Yang, Eting Yuan, Hanwen Zha, Nan Tang, Lei Chen, Nicolas Scheffer, Yue Liu, Nirav Shah, Rakesh Wanga, Anuj Kumar, Wen-tau Yih, Xin Luna Dong

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

Comments NeurIPS 2024 Datasets and Benchmarks Track

2404.13948 2024-10-23 cs.CL 83%

Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations

Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Taeho Hwang, Jong C. Park

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

Comments Findings of EMNLP Camera-ready version

2410.08801 2024-10-14 cs.SE cs.IR 83%

A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation

Sebastian Simon, Alina Mailach, Johannes Dorn, Norbert Siegmund

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.IR

2409.19019 2024-10-01 cs.CL cs.LG 83%

RAGProbe: An Automated Approach for Evaluating RAG Applications

Shangeetha Sivasothy, Scott Barnett, Stefanus Kurniawan, Zafaryab Rasool, Rajesh Vasa

专题命中 RAG评测：RAG(title,abstract)；retrieval augmented generation(abstract)；分类 cs.CL

Comments 11 pages, 5 figures, 9 tables

2408.05025 2024-08-13 cs.CR cs.AI 83%

Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks

Gianluca De Stefano, Lea Schönherr, Giancarlo Pellegrino

专题命中 RAG评测：RAG(title,abstract)；retrieval augmented generation(abstract)；分类 cs.AI

2407.01370 2024-07-02 cs.CL 83%

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

Philippe Laban, Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu

专题命中 RAG评测：RAG(title,abstract)；retriever(abstract)；分类 cs.CL

2402.07688 2024-06-04 cs.AI cs.CR 83%

CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge

Norbert Tihanyi, Mohamed Amine Ferrag, Ridhi Jain, Tamas Bisztray, Merouane Debbah

专题命中 RAG评测：retrieval-augmented generation(title,abstract)；RAG(abstract)；分类 cs.AI

2403.18350 2024-05-31 cs.CL 83%

Evaluation of Semantic Search and its Role in Retrieved-Augmented-Generation (RAG) for Arabic Language

Ali Mahboub, Muhy Eddin Za'ter, Bashar Al-Rfooh, Yazan Estaitia, Adnan Jaljuli, Asma Hakouz

专题命中 RAG评测：RAG(title,abstract)；retrieval augmented generation(abstract)；分类 cs.CL

2403.10446 2024-03-18 cs.CL cs.LG 83%

Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases

Jiarui Li, Ye Yuan, Zehua Zhang

专题命中 RAG评测：RAG(title,abstract)；retrieval augmented generation(abstract)；分类 cs.CL

Comments These authors contributed equally to this work

2608.09507 2026-08-13 cs.CL cs.AI 版本更新 82%

Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning

通过语言强化学习实现大语言模型个性化的偏好适配学习

Yuting Liu, Wei Wu, Jianzhe Zhao, Guibing Guo

专题命中 RAG评测：RAG(summary_cn,abstract)；分类 cs.CL、cs.AI

AI总结本研究针对LLM个性化中通用偏好摘要冗余问题，提出无训练元学习框架AlignXada，经语言强化学习优化后在多任务多模型上提升性能且适配效果优于RAG。

2607.26075 2026-07-30 cs.IR cs.AI 新提交 82%

IDP AutoOpt: Agent-Driven Optimization of Document Processing Pipeline Configurations

IDP AutoOpt：智能文档处理流水线配置的智能体驱动优化

David Kaleko, Sergey Ivanov, Md Mofijul Islam

专题命中 RAG评测：RAG(summary_cn,abstract)；分类 cs.IR、cs.AI

AI总结 IDP AutoOpt是自主LLM智能体，通过闭环流程优化IDP流水线配置，在多领域任务上性能优于人类专家且成本更低，还可扩展至RAG等其他企业AI系统。

2605.25920 2026-05-26 cs.CL cs.AI 82%

Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning

LLM 能时间旅行吗？通过强化学习增强法律智能搜索中的时间一致性

Wei Fan, Yining Zhou, Mufan Zhang, Yanbing Weng, Yiran HU, Tianshi Zheng, Baixuan Xu, Chunyang Li, Jianhui Yang, Haoran Li, Yangqiu Song

机构 * Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China（香港科技大学计算机科学与工程系）； School of Law, Tsinghua University, Beijing, China（清华大学法学院）； Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada（滑铁卢大学丘成桐计算机科学系）

专题命中 RAG评测：RAG(summary_cn,abstract)；分类 cs.CL、cs.AI

AI总结提出 LegalSearch-R1 框架，结合本地 statute RAG 和在线搜索，通过强化学习在跨修订期数据上训练，以解决法律 LLM 的时间偏差和搜索代理缺乏时间约束的问题，在13项法律任务上超越现有方法。

Comments Under Review

2312.14335 2026-01-06 cs.CL cs.IR 82%

Context-aware Decoding Reduces Hallucination in Query-focused Summarization

上下文感知解码减少查询导向摘要中的幻觉

Zhichao Xu

机构 * University of Utah（犹他大学）

专题命中 RAG评测：retrieval augmented generation(abstract)；RAG(abstract)；retriever(abstract)；dense retrieval(abstract)

AI总结本文提出上下文感知解码方法，通过减少查询导向摘要中的幻觉并保留词法模式匹配度，提升生成质量。

Comments technical report

2607.24010 2026-07-28 cs.LG 新提交 82%

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost

主动检索生成式人工智能何时应进行检索？效用、校准和成本的预算感知评估

Pin Qian, Su Wang, Chong Peng, Junxian You, Lifei Liu, Haoran Yu, Yihang Chen, Xiaochong Jiang

机构 * Carnegie Mellon University（卡内基梅隆大学）； University of Glasgow（格拉斯哥大学）； Georgia Institute of Technology（佐治亚理工学院）

专题命中 RAG评测：RAG(title,abstract)

AI总结研究主动检索生成式人工智能何时检索，通过将其重述为效用估计进行预算感知评估，并分离出相关三个问题，利用多种方法实现，在多数据集和模型中验证，强调评估应报告多方面指标。

Comments Accepted at the ACM SIGKDD KDD 2026 Workshop on Evaluation and Trustworthiness of Agentic AI; 7 pages, 1 figure, and 4 tables

2603.09497 2026-03-11 cs.SE 82%

EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG

EmbC-Test: 如何利用LLMs和RAG加速嵌入式软件测试

Maximilian Harnot, Sebastian Komarnicki, Michal Polok, Timo Oksanen

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)

AI总结本文提出利用LLMs和RAG技术，通过生成自动测试用例，显著提高嵌入式软件测试效率，节省66%的测试时间并每小时生成270个测试用例。

Journal ref Technical University of Munich. 2026. ISBN 978-3-911430-12-8. https://mediatum.ub.tum.de/1846559

2503.13654 2026-03-03 cs.SE cs.CR 82%

SOSecure: Safer Code Generation with RAG and StackOverflow Discussions

SOSecure: 借助检索增强生成与StackOverflow讨论实现更安全的代码生成

Manisha Mukherjee, Vincent J. Hellendoorn

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)

AI总结 SOSecure通过检索增强生成与StackOverflow讨论提升代码安全性，实现71.7%-96.7%的修复率，优于其他基线方法。

2601.10923 2026-01-22 cs.CR cs.HC 82%

Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAG

隐于 plain-text：一种用于 RAG 中社会网络间接提示注入的基准测试

Haoze Guo, Ziqi Wei

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)

AI总结 OpenRAG-Soc 提供了一种用于评估 RAG 系统在社会网络间接提示注入攻击下的基准测试工具，通过标准化的端到端评估和可部署的缓解措施，帮助从业者跟踪风险并增强部署安全性。

Comments WWW 2026

2507.20136 2026-01-21 cs.CL cs.AI cs.IR 82%

Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG

多阶段验证导向框架用于缓解多模态RAG中的幻觉

Baiyu Chen, Wilson Wongso, Xiaoqian Hu, Yue Tan, Flora Salim

机构 * The University of New South Wales（新南威尔士大学）

专题命中 RAG评测：RAG(title,abstract)；分类 cs.IR、cs.CL、cs.AI

AI总结本文提出了一种多阶段验证导向框架，通过优先考虑事实准确性和真实性来缓解多模态RAG中的幻觉问题，并在KDD Cup 2025中取得第三名。

Comments KDD Cup 2025 Meta CRAG-MM Challenge: Third Prize in the Single-Source Augmentation Task

2601.02522 2026-01-13 cs.SE 82%

On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment

在RAG系统中减少能耗的所提技术有效性：一项受控实验

Zhinuan Guo, Chushu Gao, Justus Bogner

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)

AI总结本研究通过受控实验评估了五种减少RAG系统能耗的技术，发现调整检索阈值和减少嵌入尺寸能有效降低能耗与延迟，同时保持准确率。

Comments Accepted for publication at the 2026 International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS'26)

2601.06779 2026-01-13 cs.CR 82%

CyberLLM-FINDS 2025: Instruction-Tuned Fine-tuning of Domain-Specific LLMs with Retrieval-Augmented Generation and Graph Integration for MITRE Evaluation

CyberLLM-FINDS 2025：基于检索增强生成和图集成的领域特定LLM指令微调方法用于MITRE评估

Vasanth Iyer, Leonardo Bobadilla, S. S. Iyengar

专题命中 RAG评测：retrieval-augmented generation(title,abstract)；RAG(abstract)

AI总结本文提出了一种基于检索增强生成和图集成的领域特定LLM微调方法，通过STIX威胁情报实现与MITRE ATT&CK技术的对齐，提升网络安全威胁情报分析的准确性。

Comments 12 pages

2511.12043 2025-11-18 cs.CR 82%

BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel

Hao Li, Jiajun He, Guangshuo Wang, Dengguo Feng, Zheng Li, Min Zhang

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)

2510.26160 2025-10-31 cs.CV 82%

CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark

Jiaqi Wang, Xiao Yang, Kai Sun, Parth Suresh, Sanat Sharma, Adam Czyzewski, Derek Andersen, Surya Appini, Arkav Banerjee, Sajal Choudhary, Shervin Ghasemlou, Ziqiang Guan, Akil Iyer, Haidar Khan, Lingkun Kong, Roy Luo, Tiffany Ma, Zhen Qiao, David Tran, Wenfang Xu, Skyler Yeatman, Chen Zhou, Gunveer Gujral, Yinglong Xia, Shane Moon, Nicolas Scheffer, Nirav Shah, Eun Chang, Yue Liu, Florian Metze, Tammy Stark, Zhaleh Feizollahi, Andrea Jessee, Mangesh Pujari, Ahmed Aly, Babak Damavandi, Rakesh Wanga, Anuj Kumar, Rohit Patel, Wen-tau Yih, Xin Luna Dong

机构 * Meta Reality Labs（Meta现实实验室）； Meta Superintelligence Labs（Meta超智能实验室）； FAIR, Meta（FAIR，Meta）； Meta

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)

2509.21845 2025-09-29 cs.CV 82%

A Comprehensive Evaluation of Transformer-Based Question Answering Models and RAG-Enhanced Design

Zichen Zhang, Kunlong Zhang, Hongwei Ruan, Yiming Luo

机构 * Machine Learning, ICML（机器学习，ICML）

专题命中 RAG评测：RAG(title)；retrieval-augmented generation(abstract)；hybrid retrieval(abstract)

1. RAG评测 1199 篇

OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain

Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables

LLM as HPC Expert: Extending RAG Architecture for HPC Data

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

VISA: Retrieval Augmented Generation with Visual Source Attribution

ORAssistant: A Custom RAG-based Conversational Assistant for OpenROAD

CRAG -- Comprehensive RAG Benchmark

Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations

A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation

RAGProbe: An Automated Approach for Evaluating RAG Applications

Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge

Evaluation of Semantic Search and its Role in Retrieved-Augmented-Generation (RAG) for Arabic Language

Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases

Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning

IDP AutoOpt: Agent-Driven Optimization of Document Processing Pipeline Configurations

Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning

Context-aware Decoding Reduces Hallucination in Query-focused Summarization

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost

EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG

SOSecure: Safer Code Generation with RAG and StackOverflow Discussions

Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAG

Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG

On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment

CyberLLM-FINDS 2025: Instruction-Tuned Fine-tuning of Domain-Specific LLMs with Retrieval-Augmented Generation and Graph Integration for MITRE Evaluation

BudgetLeak: Membership Inference Attacks on RAG Systems via the Generation Budget Side Channel

CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark

A Comprehensive Evaluation of Transformer-Based Question Answering Models and RAG-Enhanced Design