RAG / 检索增强生成 - arXivDaily 专题

2602.09442 2026-02-11 cs.CL cs.AI 84%

Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts

评估RAG系统中的社会偏见：当外部上下文有助于而推理有害

Shweta Parihar, Lu Cheng

机构 * University of Illinois at Chicago（伊利诺伊大学芝加哥分校）

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

AI总结本研究评估RAG系统中的社会偏见，发现外部上下文可减少偏见，但链式思维提示反而增加偏见，凸显了需要偏见意识推理框架的重要性。

Comments Accepted as a full paper with an oral presentation at the 30th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2026)

2601.15487 2026-01-23 cs.AI cs.CL cs.MA 84%

MiRAGE: A Multiagent Framework for Generating Multimodal Multihop Question-Answer Dataset for RAG Evaluation

MiRAGE：一种多智能体框架，用于生成多模态多跳问题-答案数据集以评估RAG系统

Chandan Kumar Sahu, Premith Kumar Chilukuri, Matthew Hetrich

机构 * ABB Inc（ABB公司）

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

AI总结 MiRAGE通过多智能体框架生成多模态多跳问题-答案数据集，提升RAG系统评估的准确性和复杂性。

Comments 12 pages, 2 figures, Submitted to ACL

2502.16101 2026-01-21 cs.AI cs.IR 84%

Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals

比零样本更差？一个评估RAG在误导检索中鲁棒性的事实核查数据集

Linda Zeng, Rithwik Gupta, Divij Motwani, Yi Zhang, Diji Yang

机构 * The Harker School（哈克尔学校）； Irvington High School（艾尔文顿高中）； Palo Alto High School（帕洛阿尔托高中）； University of California Santa Cruz（加州大学圣克鲁兹分校）

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

AI总结 RAGuard是首个评估RAG系统在误导检索中鲁棒性的基准，揭示LLM在面对误导信息时的表现劣于零样本基线。

Comments Advances in Neural Information Processing Systems (NeurIPS 2025)

2601.04196 2026-01-09 cs.CL cs.IR 84%

RAGVUE: A Diagnostic View for Explainable and Automated Evaluation of Retrieval-Augmented Generation

RAGVUE：一种用于可解释和自动评估检索增强生成的诊断视图

Keerthana Murugaraj, Salima Lamsiyah, Martin Theobald

机构 * University of Luxembourg（卢森堡大学）

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

AI总结 RAGVUE通过分解RAG行为并提供结构化解释，实现无参考的自动评估，揭示RAG流程中的细粒度失败。

2512.15068 2025-12-22 cs.LG cs.AI cs.CL 84%

The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems

语义幻觉：基于嵌入的幻觉检测在RAG系统中的认证极限

Debu Sinha

机构 * Independent Researcher（独立研究者）

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

AI总结研究揭示了基于嵌入的幻觉检测在RAG系统中存在语义幻觉问题，通过符合预测方法发现真实幻觉检测的挑战，证明需通过推理而非表面语义解决。

Comments 12 pages, 3 figures, 5 tables

2409.12524 2025-12-19 cs.CL cs.AI 84%

Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting

通过记忆重要性与遗忘的心理模型增强长期RAG聊天机器人

Ryuichi Sumida, Koji Inoue, Tatsuya Kawahara

机构 * Graduate School of Informatics Kyoto University（京都大学信息学研究科）

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

AI总结 LUFY通过优先保留情绪唤醒记忆并遗忘大部分对话内容，提升长期对话体验和聊天机器人性能。

Comments 37 pages, accepted and published in Dialogue & Discourse 16(2) (2025)

Journal ref Dialogue & Discourse 16(2) (2025) 74--110

2512.01335 2025-12-02 cs.CR cs.AI cs.CL 84%

EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations

EmoRAG：评估RAG对符号扰动的鲁棒性

Xinyun Zhou, Xinfeng Li, Yinan Peng, Ming Xu, Xuanwang Zhang, Miao Yu, Yidong Wang, Xiaojun Jia, Kun Wang, Qingsong Wen, XiaoFeng Wang, Wei Dong

机构 * ZJU Hangzhou China（浙江大学杭州校区）； NTU Singapore（南洋理工大学）； Hengxin Tech. Singapore（新加坡恒心科技）； NUS Singapore（国立新加坡大学）； NJU Nanjing China（南京大学）； PKU Beijing China（北京大学）

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

AI总结 EmoRAG研究揭示RAG系统对细微表情符号扰动的鲁棒性问题，发现单个表情符号可导致检索严重误导，并提出针对性防御措施。

Comments Accepted to ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2026

2511.14531 2025-11-19 cs.CL cs.IR 84%

LiveRAG: A diverse Q&A dataset with varying difficulty level for RAG evaluation

David Carmel, Simone Filice, Guy Horowitz, Yoelle Maarek, Alex Shtoff, Oren Somekh, Ran Tavory

机构 * Technology Innovation Institute (TII)（技术创新研究所）

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

Comments 14 pages, 4 figures, 5 tables

2508.14066 2025-11-19 cs.IR cs.AI 84%

Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation

Lorenz Brehme, Benedikt Dornauer, Thomas Ströhle, Maximilian Ehrhart, Ruth Breu

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

Comments This preprint was accepted for presentation at the 17th International Conference on Knowledge Discovery and Information Retrieval (KDIR25)

2511.04502 2025-11-07 cs.CL cs.AI 84%

RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG

Joshua Gao, Quoc Huy Pham, Subin Varghese, Silwal Saurav, Vedhus Hoskere

机构 * University of Houston（德克萨斯大学休斯敦分校）

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

2505.04847 2025-11-07 cs.CL cs.AI 84%

Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards

Manveer Singh Tamber, Forrest Sheng Bao, Chenyu Xu, Ge Luo, Suleman Kazi, Minseok Bae, Miaoran Li, Ofer Mendelevitch, Renyi Qu, Jimmy Lin

机构 * University of Waterloo（滑铁卢大学）； Vectara（Vectara公司）； Iowa State University（爱荷华州立大学）； Stanford University（斯坦福大学）

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

Comments EMNLP Industry Track 2025

2511.03261 2025-11-06 cs.CL cs.AI 84%

Comparing the Performance of LLMs in RAG-based Question-Answering: A Case Study in Computer Science Literature

Ranul Dayarathne, Uvini Ranaweera, Upeksha Ganegoda

机构 * University of Moratuwa（穆塔瓦大学）

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

Comments 18 pages, 4 figures, 5 tables, presented at the 5th International Conference on Artificial Intelligence in Education Technology

Journal ref Lecture Notes on Data Engineering and Communications Technologies, vol. 228, Springer, 2025, pp. 387--403

2510.26205 2025-11-05 cs.CL cs.AI 84%

Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning

Qi Luo, Xiaonan Li, Tingshuo Fan, Xinchi Chen, Xipeng Qiu

机构 * Fudan University（复旦大学）； Shanghai Innovation Institute（上海创新研究院）

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

2510.24476 2025-10-29 cs.CL cs.AI 84%

Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems

Yihan Li, Xiyuan Fu, Ghanshyam Verma, Paul Buitelaar, Mingming Liu

机构 * Electronic Information School, Wuhan University（武汉大学电子信息学院）； School of Computing, Dublin City University（都柏林城市大学计算机学院）； School of Public Health, Wuhan University（武汉大学公共卫生学院）； Insight Centre for Data Analytics, University of Galway（Galway大学数据分析研究中心）； Insight Centre for Data Analytics, Dublin City University（都柏林城市大学数据分析研究中心）

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

Comments 25 pages, 7 figures, 3 tables

2508.17225 2025-10-07 cs.CL cs.AI 84%

SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation

Xiaqiang Tang, Yi Wang, Keyu Hu, Rui Xu, Chuang Li, Weigao Sun, Jian Li, Sihong Xie

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Chinese Academy of Sciences（中国科学院）； Shanghai AI Lab（上海人工智能实验室）； Tencent Hunyuan（腾讯文英）

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

Comments Working in progress

2510.02549 2025-10-06 cs.CL cs.AI 84%

Knowledge-Graph Based RAG System Evaluation Framework

Sicheng Dong, Vahid Zolfaghari, Nenad Petrovic, Alois Knoll

机构 * Technical University of Munich, Robotics, Artificial Intelligence and Embedded Systems（慕尼黑技术大学，机器人，人工智能与嵌入式系统）

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

2509.14435 2025-09-26 cs.CL cs.IR 84%

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG

Harshad Khadilkar, Abhay Gupta

机构 * Indian Institute of Technology Bombay（印度理工学院班加罗尔分校）； Indian Institute of Technology Patna（印度理工学院帕纳姆分校）

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

2509.17671 2025-09-23 cs.CL cs.AI 84%

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

Selva Taş, Mahmut El Huseyni, Özay Ezerceli, Reyhan Bayraktar, Fatma Betül Terzioğlu

机构 * Hidden for Review（保密）

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

2410.16322 2025-09-23 cs.CL cs.AI cs.HC 84%

SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques

Qiming Guo, Jinwen Tang, Wenbo Sun, Haoteng Tang, Yi Shang, Wenlu Wang

机构 * Texas A&M University - Corpus Christi（德克萨斯A&M大学-科珀斯克里斯蒂分校）； University of Missouri（密苏里大学）； Delft University of Technology（代尔夫特理工大学）； University of Texas Rio Grande Valley（德克萨斯大学里奥格兰德谷分校）

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

Comments 26 pages, 19 figures, 8 tables

2509.12168 2025-09-16 cs.CL cs.AI 84%

RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing

Timothy Rupprecht, Enfu Nan, Arash Akbari, Arman Akbari, Lei Lu, Priyanka Maan, Sean Duffy, Pu Zhao, Yumei He, David Kaeli, Yanzhi Wang

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系）； Northeastern University（东北大学）； Tulane University（路易斯安那州立大学）

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

2508.13107 2025-09-11 cs.CL cs.IR 84%

All for law and law for all: Adaptive RAG Pipeline for Legal Research

Figarri Keisha, Prince Singh, Pallavi, Dion Fernandes, Aravindh Manivannan, Ilham Wicaksono, Faisal Ahmad, Wiem Ben Rim

机构 * University College London（伦敦大学学院）

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

Comments submitted to NLLP 2025 Workshop

2509.07475 2025-09-10 cs.CL cs.AI 84%

HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention

Saumya Goswami, Siddharth Kurra

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

2506.02037 2025-09-03 cs.CL cs.AI 84%

FinS-Pilot: A Benchmark for Online Financial RAG System

Feng Wang, Yiding Sun, Jiaxin Mao, Wei Xue, Danqing Xu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高陵人工智能学院）； Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大型模型与智能治理研究重点实验室）； Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程研究中心，教育部）； Tencent Inc.（腾讯公司）

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

2508.18929 2025-08-27 cs.CL cs.AI 84%

Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework

Ilias Driouich, Hongliu Cao, Eoin Thomas

机构 * AMADEUS France（AMADEUS法国）

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

Comments ECAI 2025 TRUST AI workshop

2504.20119 2025-08-08 cs.IR cs.AI 84%

Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets

Lorenz Brehme, Thomas Ströhle, Ruth Breu

机构 * Department of Computer Science University of Innsbruck（计算机科学系因斯布鲁克大学）

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

Comments 8 Pages. This paper has been accepted for presentation at the IEEE Swiss Conference on Data Science (SDS25)

2502.17163 2025-07-22 cs.CL cs.AI 84%

MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation

María Andrea Cruz Blandón, Jayasimha Talur, Bruno Charron, Dong Liu, Saab Mansour, Marcello Federico

机构 * Tampere University（塔尔皮奥大学）； Amazon（亚马逊）

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

Comments ACL 2025

2503.04800 2025-07-21 cs.CL cs.AI 84%

HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation

Jie Ouyang, Tingyue Pan, Mingyue Cheng, Ruiran Yan, Yucong Luo, Jiaying Lin, Qi Liu

机构 * State Key Lab 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）

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

2501.08208 2025-07-21 cs.CL cs.AI 84%

ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems

Mohita Chowdhury, Yajie Vera He, Jared Joselowitz, Aisling Higham, Ernest Lim

机构 * Ufonia Limited（乌菲尼亚有限公司）； University of York（约克大学）

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

Comments 29 pages

2503.00781 2025-07-03 cs.IR cs.AI 84%

Towards Efficient Educational Chatbots: Benchmarking RAG Frameworks

Umar Ali Khan, Ekram Khan, Fiza Khan, Athar Ali Moinuddin

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

Comments One of the co-authors is having conflict in the submission to arXiv due to many edits (we have to make changes in evaluation strategies, i.e. section 5); in the paper there are still formatting issues

2506.21569 2025-06-30 cs.CL cs.AI 84%

Hybrid-NL2SVA: Integrating RAG and Finetuning for LLM-based NL2SVA

Weihua Xiao, Derek Ekberg, Siddharth Garg, Ramesh Karri

机构 * NYU Tandon School of Engineering（纽约大学Tandon工程学院）

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

1. RAG评测 1223 篇

Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts

MiRAGE: A Multiagent Framework for Generating Multimodal Multihop Question-Answer Dataset for RAG Evaluation

Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals

RAGVUE: A Diagnostic View for Explainable and Automated Evaluation of Retrieval-Augmented Generation

The Semantic Illusion: Certified Limits of Embedding-Based Hallucination Detection in RAG Systems

Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting

EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations

LiveRAG: A diverse Q&A dataset with varying difficulty level for RAG evaluation

Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation

RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG

Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards

Comparing the Performance of LLMs in RAG-based Question-Answering: A Case Study in Computer Science Literature

Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning

Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems

SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation

Knowledge-Graph Based RAG System Evaluation Framework

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques

RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing

All for law and law for all: Adaptive RAG Pipeline for Legal Research

HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention

FinS-Pilot: A Benchmark for Online Financial RAG System

Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework

Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets

MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation

HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation

ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems

Towards Efficient Educational Chatbots: Benchmarking RAG Frameworks

Hybrid-NL2SVA: Integrating RAG and Finetuning for LLM-based NL2SVA