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. Reading Beyond OCR Noise: Robust Cross-Lingual RAG for Legislative Archives

    Oct 26, 2026Radha Krishna Deshpande, Ajoy Mondal, Akash Manna +1Historical Document ProcessingRAG Robustness

    CVIT, International Institute of Information Technology, Hyderabad, India

  2. Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization

    Oct 26, 2026Hangyi Zhao, Bonan Zhang, Fusen Guo +3RAG Poisoning AttacksAdversarial Text Attacks

    Faculty of Data Science, City University of Macau, Macau, China · School of Systems and Computing, UNSW Sydney, Canberra, Australia · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1

  3. Factual Yet One-Sided: Stance Poisoning and Evidence Balancing in Retrieval-Augmented Generation

    Oct 25, 2026Puyuan Yang, Shaoxuan Dong, Liujie Wu +2RAG Poisoning AttacksRAG Robustness

    Department of Computer Science, Swansea University, Swansea, United Kingdom · School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China

  4. Ranking Is Not Deciding: Benchmark Shortcuts and Operating-Point Collapse in Query-Time RAG Poisoning Defenses

    Oct 24, 2026Pushkal Kumar, Arvin SahaymRAG SecurityRAG Robustness

    North Creek High School · Washington State University

  5. TriageRAG: Failure-Aware Self-Training for Adapting Retrieval-Augmented Language Models to Specialized Domains

    Oct 24, 2026Samarth Varshney, Ritu YadavRetrieval-Augmented GenerationDomain Adaptation for LLMs

  6. Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5

    Oct 24, 2026Georgios Feretzakis, Alexandros PapaspyridisLLM ReliabilityRAG Security

  7. KrishokTech: A Bengali Agricultural Advisory System with Explicit Authorization Controls

    Oct 23, 2026Khan Raiyan Ibne Reza, Sanjana Aktar Maria, Shakil Ahmed +2LLM GuardrailsAI-Assisted Decision Making

    Department of Computer Science and Engineering, North South University, Dhaka 1229, Bangladesh

  8. From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning

    Oct 23, 2026Masoud Monajatipoor, Fazlolah Mohaghegh, Hamid Reza Hassanzadeh +2Retrieval-Augmented ICLIn-Context Learning

    Optum AI

  9. Joint Constraint Aggregation for Qualifier-Sensitive Retrieval-Augmented QA

    Oct 19, 2026Jennifer Hsia, Zachary C. Lipton, Aarti SinghRetrieval-Augmented GenerationRAG Robustness

    Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213, USA

  10. Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning

    Oct 14, 2026Hui Zhang, Yujia Zeng, Yuhao XinMedical ReasoningLLM Routing

    Beijing Institute of Technology · Shanghai Jiao Tong University · Xi’an Jiaotong University

  11. GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation

    Oct 14, 2026Yining Tang, Junyu Zhang, Haomiao Qiu +5Graph Retrieval-Augmented GenerationRAG Security

    Zhejiang University · Harbin Institute of Technology, Shenzhen · Great Bay University +1

  12. TRACER: Trace-Regularized Training Against Indirect Prompt Injection

    Oct 13, 2026Kshitij Mishra, Salem Lahlou, Nils LukasIndirect Prompt InjectionPrompt Injection Defense

    Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates

  13. Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision Support

    Oct 8, 2026Federico Mazzoni, Andrea FaillaHuman-AI Decision MakingRetrieval-Augmented Generation

    Independent Researcher · Institute of Information Science and Technologies (ISTI), National Research Council (CNR), Italy

  14. RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation

    Oct 8, 2026Shunyuan Zhou, Hao Chen, Tianyu Wang +3Retrieval-Augmented GenerationRAG Evaluation

    Beijing University of Posts and Telecommunications · Humanlaya Data · Beijing Key Laboratory of Key Technologies for AI+ Domain Applications +1

  15. Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek

    Oct 6, 2026Nikolaos D. Tantaroudas, Ilias Karachalios, Andrew J. McCrackenRAG RobustnessRetrieval-Augmented Generation

    Institute of Communication and Computer Systems (ICCS), National Technical University of Athens, 9 Iroon Polytechniou Str., 15773 Zografou, Athens, Greece · University of Thessaly, 413 34 Larisa, Greece · DASKALOS-APPS, 183 Rue de l’Abbé Griffon, 01960, Péronnas, France

  16. RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation

    Oct 3, 2026Shiqi Yang, Jiekai Ma, Gaoyuan DuRetrieval-Augmented GenerationRAG Evaluation

    Amazon

  17. Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email Agents

    Oct 2, 2026Feng Chen, Ritam Dutt, Atnaz Taheri +1LLM Agent ReliabilityLLM Agent Evaluation

  18. Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM

    Oct 1, 2026Jisung Park, John Le, Heath CooperRAG Poisoning AttacksGraph Retrieval-Augmented Generation

    Institute of Cybersecurity and Cryptology, University of Wollongong

  19. Rethinking Knowledge Retrieval for Generation: A Survey on RAG Architectures and Applications

    Oct 1, 2026Meghana Sunil, Shravya V, Shravan Venkatraman +1Retrieval-Augmented GenerationRAG Security

    School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India. · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.

  20. RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage

    Sep 30, 2026Zeming Liu, Qibai Chen, Jingtao Zhang +1Hallucination in RAGSelective Prediction

    Brown University, United States · Independent Researcher, United States · Georgia Institute of Technology, United States

  21. Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG

    Sep 29, 2026Pranav Handa, Ariful AzadRetrieval-Augmented GenerationLLM Reliability

    Texas A&M University

  22. Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction

    Sep 27, 2026Prasanjit Dubey, Aritra Guha, Xiaoming HuoRetrieval-Augmented GenerationFederated Conformal Prediction

    H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332, U.S.A. · AT&T Chief Data Office

  23. Regime Boundary Alignment for Evidence-Gated Question Answering

    Sep 25, 2026Zeyan Li, Qirong Guo, SIyuan Qiu +3Evidence-Grounded QALLM Grounding

    Shanghai Jiao Tong University · The Hong Kong University of Science and Technology (Guangzhou)

  24. Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers

    Sep 25, 2026Md Shamim Ahmed, Lukas Galke Poech, Richard RöttgerRAG Poisoning AttacksRAG Robustness

    University of Southern Denmark

  25. Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation

    Sep 24, 2026Zhengchen Huang, Yundong Sun, Minrui Song +4RAG RobustnessRetrieval-Augmented Generation

    School of Information Science & Engineering, LinYi University, China · School of Computer Science and Technology, Harbin Institute of Technology, China

  26. When Retrieval Hurts: Measuring and Explaining Retrieval-Induced Hallucination in Chest X-ray Report Generation

    Sep 22, 2026Emmanuel Idoko, Abdusshakur Olabisi, Shiloh Oni +1Hallucination in Language ModelsRAG Robustness

    University of Lagos · Machine Learning Collective · NITHUB, University of Lagos +2

  27. RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation

    Sep 21, 2026Abdullahil Kafi, Alvi Ataur KhalilRAG Poisoning AttacksRAG Security

    Transformative Innovation for Trustworthy AI and Network Security (TITANS) Lab, Computer Science, Southern Illinois University, USA

  28. Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems

    Sep 18, 2026Pedro Pereira, Eva Maia, Isabel PraçaRAG Poisoning AttacksRAG Robustness

    GECAD, ISEP, Polytechnic of Porto, Rua Dr. António Bernardino de Almeida, 4249-015 Porto, Portugal

  29. Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention

    Sep 17, 2026Jongbin Won, Sung Geun An, Jay-yoon LeeLLM AbstentionRAG Robustness

    Graduate School of Data Science / Seoul National University

  30. CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering

    Sep 14, 2026Sumit Barua, Guan Hong, Halil Dursunoglu +2Retrieval-Augmented GenerationCitation Verification

    Department of Computer Science, Western Michigan University, Kalamazoo, MI, 49008, USA.