mlsanityData to 7 Oct 2026

RAGGED: Towards Informed Design of Scalable and Stable RAG Systems

arXiv 2403.09040 ↗First posted 14 Mar 2024cs.CLcited by 24

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances language models by integrating external knowledge, but its effectiveness is highly dependent on system configuration. Improper retrieval settings can degrade performance, making RAG less reliable than closed-book generation. In this work, we introduce RAGGED, a framework for systematically evaluating RAG systems across diverse retriever-reader configurations, retrieval depths, and datasets. Our analysis reveals that reader robustness to noise is the key determinant of RAG stability and scalability. Some readers benefit from increased retrieval depth, while others degrade due to their sensitivity to distracting content. Through large-scale experiments on open-domain, multi-hop, and specialized-domain datasets, we show that retrievers, rerankers, and prompts influence performance but do not fundamentally alter these reader-driven trends. By providing a principled framework and new metrics to assess RAG stability and scalability, RAGGED enables systematic evaluation of retrieval-augmented generation systems, guiding future research on optimizing retrieval depth and model robustness.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 18 references that are in the map. First posted on arXiv 14 Mar 2024.

Builds on

10 of 18 references.

References · 10

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  5. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  6. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  7. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  8. 2022UL2: Unifying Language Learning Paradigmscited by 292
  9. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  10. 2024The Chronicles of RAG: The Retriever, the Chunk and the Generatorcited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 8; 2026: 9.

24 papers.

Sort:

By area:

  1. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacycited by 38
  2. 2024BERGEN: A Benchmarking Library for Retrieval-Augmented Generationcited by 31
  3. 2024Context Embeddings for Efficient Answer Generation in RAGcited by 26
  4. 2025Provence: efficient and robust context pruning for retrieval-augmented generationcited by 25
  5. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 25
  6. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practicescited by 22
  7. 2025PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluationcited by 14
  8. 2024Beyond Scaling Laws: Understanding Transformer Performance with Associative Memorycited by 12
  9. 2024RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generationcited by 5
  10. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  11. 2024Toward Optimal Search and Retrieval for RAGcited by 4
  12. 2024Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Modelscited by 3
12 more
  1. 2025RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelinescited by 3
  2. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generationcited by 3
  3. 2025Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewardscited by 2
  4. 2025Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systemscited by 1
  5. 2026PRISM: Fast Online LLM Serving via Scheduling-Memory Co-designcited by 1
  6. 2026Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluationcited by 1
  7. 2026Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152cited by 0
  8. 2026MegaMem: A Retrieval Solution for Ultra-Large Context Windowscited by 0
  9. 2026Assessing the Downstream Utility of Evidence-Aware Retrieval in RAGcited by 0
  10. 2026Cross Lingual Transfer in Tulu Legal Comprehension: Script-Dependent Improvement and RAG-Induced Knowledge Conflictcited by 0
  11. 2026SocialBuddy: Tailoring Search Agent for Social Scenarioscited by 0
  12. 2026When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  2. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
  3. 2025Evaluating the Retrieval Robustness of Large Language Models
  4. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  5. 2026Revisiting RAG Retrievers: An Information Theoretic Benchmark
  6. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  7. 2025PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation
  8. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs