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. Enhancing Legal LLMs through Metadata-Enriched RAG Pipelines and Direct Preference Optimization

    Feb 25, 2026Suyash Maniyar, Deepali Singh, Rohith ReddyLLM GroundingLanguage Modeling

  2. ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation

    Feb 24, 2026Sunguk Shin, Meeyoung Cha, Byung-Jun Lee +1RAG RobustnessLLM Abstention

    Korea University, Seoul, South Korea · MPI-SP, Bochum, Germany · KAIST, Daejeon, South Korea +1

  3. Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem

    Feb 21, 2026Lichang Song, Ting Long, Yi ChangRetrieval-Augmented GenerationRAG Robustness

    Jilin University

  4. Enhancing Large Language Models (LLMs) for Telecom using Dynamic Knowledge Graphs and Explainable Retrieval-Augmented Generation

    Feb 19, 2026Dun Yuan, Hao Zhou, Xue Liu +4Knowledge Augmentation for Language ModelsGraph Retrieval-Augmented Generation

    Charlie · School of Computer Science, McGill University, Montreal, QC H3A 0E9, Canada. · Standards and Mobility Innovation Lab, Samsung Research America, Plano, Texas, TX 75023, USA.

  5. Retrieval Collapses When AI Pollutes the Web

    Feb 18, 2026Hongyeon Yu, Dongchan Kim, Young-Bum KimInformation RetrievalRAG Robustness

    NAVER Corp. Bellevue, WA, USA

  6. Panini: Continual Learning in Token Space via Structured Memory

    Feb 16, 2026Shreyas Rajesh, Pavan Holur, Mehmet Yigit Turali +2Continual Learning for LLMsMemory-Augmented Language Models

    Department of Electrical and Computer Engineering, University of California, Los Angeles, USA.

  7. Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

    Oct 1, 2025Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1Language Model SteeringRAG Poisoning Attacks

    CyCraft AI Lab, Taiwan · National Taiwan University

  8. SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generation with LLMs

    Aug 12, 2025Haotian Chen, Qingqing Long, Meng Xiao +6LLM RerankingRAG Evaluation

    Computer Network Information Center, Chinese Academy of Sciences · University of California, Los Angeles · Peking University