RAG Robustness

RAG: Retrieval-Augmented Generation

Ask about this topic

Overview

This field studies how retrieval-augmented generation systems behave when evidence is noisy, stale, missing, contradictory, or deliberately poisoned, and when queries or conversations vary. Common approaches detect and filter unreliable documents, rerank by trust or provenance, verify claims against evidence, and teach models to select evidence or abstain when support is weak. Researchers evaluate these methods with controlled corruption and poisoning tests, as well as benchmarks for uncertainty, query variation, multimodal inputs, and multi-turn use. A central tension is that stronger retrieval or stricter filtering can improve resistance to misleading evidence but also discard useful context, add cost, or still fail to ensure that detected conflicts are resolved safely.

Latest papers

CardsList

128 papers19 papers in the last four weeks, down 5% on the four weeks before. 0.1% of all new papers.

  1. RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generation

    Aug 13, 2026Xinlong Xu, Yoshua Y. LiRAG Poisoning AttacksRAG Security

    Nanjing University of Information Science and Technology · Meituan

  2. EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval

    Aug 12, 2026Huiqi Miao, Xinbao Sun, Bo Wang +6Retrieval-Augmented GenerationInstruction Following

    Jiutian Research, China Mobile, Beijing, China

  3. PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates

    Aug 5, 2026Zijian Wang, Yubo Zhu, Muzhi Dong +7Knowledge Conflicts in Language ModelsRAG Poisoning Attacks

    School of Computer Science, Nanjing University, Nanjing 210023, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China

  4. LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation

    Jul 29, 2026Musa ShamsAI Agent ReliabilityRetrieval-Augmented Generation

    Independent Researcher

  5. RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning

    Jul 28, 2026Pushkal Kumar, Tucker Nielson, Tanish Kolhe +2RAG Poisoning AttacksRAG Security

  6. TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation

    Jul 26, 2026Susil Kumar Mohanty, Rohit Patel, Kosuru Yuvaraj +2Retrieval-Augmented GenerationRAG Poisoning Attacks

    Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India

  7. Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

    Jul 22, 2026Yanyu Chen, Yue Li, Yongyi Cui +2RL for Language ModelsRetrieval-Augmented Generation

    East China Normal University · Shandong University

  8. Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG

    Jul 12, 2026Saadeldine Eletter, Owais Aijaz, Preslav NakovMultimodal RAGRetrieval-Augmented Generation

    Mohamed bin Zayed University of Artificial Intelligence

  9. MIRAGE: Defending Long-Form RAG Against Misinformation Pollution

    Jul 6, 2026Saadeldine Eletter, Ruihong Zeng, Yuxia Wang +3RAG Poisoning AttacksRetrieval Robustness

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · INSAIT, Sofia University St. Kliment Ohridski

  10. Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents

    Jul 1, 2026Ádám Kovács, Bowei He, Xue Liu +3LLM GroundingHallucination Detection

    KR Labs · MBZUAI · McGill University +1

  11. Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts

    Jun 29, 2026Bo Wang, Heyan Huang, Yaolin Li +5Retrieval-Augmented GenerationKnowledge Conflicts in Language Models

    School of Computer Science, Beijing Institute of Technology

  12. Diagnosing and Repairing Factual Errors in RAG under Budget Constraints

    Jun 28, 2026Soroush Hashemifar, Havva Alizadeh Noughabi, Fattane Zarrinkalam +1Retrieval-Augmented GenerationLLM Reliability

    College of Engineering, University of Guelph, Guelph, ON, Canada · Cyber Science Lab, School of Computer Science, University of Guelph, Guelph, ON, Canada

  13. MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG

    Jun 25, 2026Inderjeet Singh, Andrés Murillo, Motoyoshi Sekiya +2Multimodal RAGTool-Augmented Language Model Agents

    Fujitsu Research of Europe, United Kingdom · Fujitsu Limited, Japan

  14. CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework

    Jun 16, 2026Sneha Rao, Shaina Raza, Dhanesh RamachandramVLM EvaluationVision-Language Grounding

    Vector Institute, Toronto, ON M5G 0C6, Canada

  15. When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval

    Jun 9, 2026Nabaraj Subedi, Ahmed Abdelaty, Shivanand Venkanna SheshappanavarRetrieval-Augmented GenerationAgentic RAG

    Dept. of Electrical Engineering & Computer Science University of Wyoming, Laramie, WY 82071, USA · Dept. of Civil, Architectural Engineering & Construction Management University of Wyoming, Laramie, WY 82071, USA

  16. Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval

    Jun 5, 2026Sevgi Yigit-SertRetrieval-Augmented GenerationKnowledge Conflicts in Language Models

    Computer Engineering Department, Ankara University, Golbasi Campus, 06830, Ankara, Turkey · Golbasi Campus, 06830, Ankara, Turkey

  17. A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation

    May 29, 2026Bharath Simha Reddy MuthyamRetrieval-Augmented GenerationRetrieval Robustness

    Independent Researcher

  18. SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning

    May 27, 2026Jiachen QianRetrieval-Augmented GenerationRAG Poisoning Attacks

    City University of Hong Kong · Hong Kong, Hong Kong

  19. Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs

    May 26, 2026Zhe Yu, Wenpeng Xing, Chen Ye +4Language Model Safety EvaluationKnowledge Conflicts in Language Models

    Binjiang Institute of Zhejiang University · Zhejiang University · Hangzhou Dianzi University +1

  20. Generating Leakage-Free Benchmarks for Robust RAG Evaluation

    May 9, 2026Jiayi Liu, Jiaxing Zhang, Bowen Jin +1Benchmark ContaminationSynthetic Benchmark Generation

    Department of Computer Science, Purdue University · New Jersey Institute of Technology · University of Illinois at Urbana-Champaign +1

  21. PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption

    May 8, 2026Xue Tan, Yi Zheng, Chang Huo +7Retrieval-Augmented GenerationRAG Poisoning Attacks

    School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China · Department of Computer Science, Worcester Polytechnic Institute, MA, USA

  22. Architecture Matters: Comparing RAG Systems under Knowledge Base Poisoning

    May 7, 2026Samuel KornRetrieval-Augmented GenerationRAG Poisoning Attacks

  23. AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation

    May 4, 2026Yilin Guo, Yinshan Wang, Yixuan WangMulti-Hop QARetrieval-Augmented Generation

    Center for Data Science New York University · Tandon School of Engineering New York University

  24. Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation

    May 2, 2026Peiyang Liu, Qiang Yan, Ziqiang Cui +3Retrieval-Augmented GenerationLLM Hallucination Mitigation

    National Engineering Research Center for Software Engineering, Peking University Beijing, China · PX Securities Shenzhen, China · City University of Hong Kong Hong Kong SAR, China +2

  25. When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation

    Apr 29, 2026Lin Sun, Wang Dexian, Jingang Huang +4RAG EvaluationOptical Character Recognition

    Beijing Qiyuan Technology

  26. RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration

    Apr 17, 2026Fabian Ridder, Laurin Lessel, Malte SchillingHallucination in Language ModelsRAG Robustness

    Computer Science Department, University of Münster, Münster, Germany

  27. Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization

    Apr 16, 2026Gongbo Zhang, Yifan Peng, Chunhua WengLLM Self-CorrectionRetrieval-Augmented Generation

    Columbia University · Weill Cornell Medicine

  28. How You Ask Matters! Adaptive RAG Robustness to Query Variations

    Apr 12, 2026Yunah Jang, Megha Sundriyal, Kyomin Jung +1Adaptive RAGRAG Robustness

    Seoul National University · Max Planck Institute for Security and Privacy, Germany

  29. Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS

    Apr 12, 2026Shijia Xu, Zhou Wu, Xiaolong Jia +3Retrieval-Augmented GenerationRAG Robustness

    Chongqing University, China · Queen Mary University of London, UK · Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing, China +1

  30. SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented Generation

    Apr 12, 2026Gyumin Kim, Juhwan Park, Jaeha Kim +3LLM Hallucination MitigationLanguage Model Error Detection

    Department of Information Communications Engineering, Hankuk University of Foreign Studies, Republic of Korea · Division of Computer Engineering, Hankuk University of Foreign Studies, Republic of Korea · Department of Statistics, Hankuk University of Foreign Studies, Republic of Korea