mlsanityData to 14 Oct 2026

Investigating the Robustness of Retrieval-Augmented Generation at the Query Level

arXiv 2507.06956 ↗First posted 9 Jul 2025cs.CLcited by 11

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Large language models (LLMs) are very costly and inefficient to update with new information. To address this limitation, retrieval-augmented generation (RAG) has been proposed as a solution that dynamically incorporates external knowledge during inference, improving factual consistency and reducing hallucinations. Despite its promise, RAG systems face practical challenges-most notably, a strong dependence on the quality of the input query for accurate retrieval. In this paper, we investigate the sensitivity of different components in the RAG pipeline to various types of query perturbations. Our analysis reveals that the performance of commonly used retrievers can degrade significantly even under minor query variations. We study each module in isolation as well as their combined effect in an end-to-end question answering setting, using both general-domain and domain-specific datasets. Additionally, we propose an evaluation framework to systematically assess the query-level robustness of RAG pipelines and offer actionable recommendations for practitioners based on the results of more than 1092 experiments we performed.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 20 of its 37 references that are in the map. First posted on arXiv 9 Jul 2025.

Builds on

20 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training31 May

Other references · 19

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  6. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  7. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  8. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  9. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  10. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  11. 2021Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representationscited by 60
  12. 2024Improving the Robustness of Large Language Models via Consistency Alignmentcited by 36
7 more
  1. 2021Evaluating the Robustness of Retrieval Pipelines with Query Variation Generatorscited by 34
  2. 2024BERGEN: A Benchmarking Library for Retrieval-Augmented Generationcited by 31
  3. 2022Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellingscited by 23
  4. 2022CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typoscited by 22
  5. 2024Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspectivecited by 15
  6. 2024ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbationcited by 10
  7. 2023On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspectivecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2025Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domaincited by 6
  2. 2026EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generationcited by 6
  3. 2026How You Ask Matters! Adaptive RAG Robustness to Query Variationscited by 3
  4. 2025Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewardscited by 2
  5. 2026Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baselinecited by 2
  6. 2026Leveraging LLM Parametric Knowledge for Fact Checking without Retrievalcited by 1
  7. 2026Spelling Correction in Healthcare Query-Answer Systems: Methods, Retrieval Impact, and Empirical Evaluationcited by 0
  8. 2026RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generationcited by 0
  9. 2026Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attackscited by 0
  10. 2026Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generationcited by 0
  11. 2026GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  2. 2025Evaluating the Retrieval Robustness of Large Language Models
  3. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  4. 2024Semantic Tokens in Retrieval Augmented Generation
  5. 2025PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation
  6. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  7. 2024Toward Optimal Search and Retrieval for RAG
  8. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions