mlsanityData to 7 Oct 2026

The Powerless Noise: How Experimental Settings Shape the Reported Power of Noise

arXiv 2607.03615 ↗First posted 3 Jul 2026cs.IRcited by 1

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

Abstract (arXiv)

Recent work has suggested that adding irrelevant documents to the input of retrieval-augmented generation (RAG) systems can improve question-answering performance, a phenomenon referred to as the Power of Noise. This motivated investigations into the role of noise in information retrieval. In this paper, we reproduce the main findings of Cuconasu et al. and evaluate the robustness of the effect under extended experimental settings. We first confirm that the phenomenon holds under the original setup, which uses earlier-generation LLMs, restrictive prompting and constrained decoding settings. We subsequently introduce a series of extensions to investigate the underlying causes of the noise effect, examining the authors' original design choices including the use of different models, instruction prompting, and relaxed output length constraints. Across these ablations, the Power-of-Noise pattern proves highly sensitive to inference configuration: it can appear, weaken, or disappear under small changes to prompt formulation and decoding limits. Combined with our error analysis, which shows substantial contributions from truncation and malformed generations, this variance indicates that the original effect cannot be robustly confirmed as a general benefit of noisy retrieval under these experimental conditions. More broadly, our work highlights the importance of carefully scrutinizing inference design in retrieval-augmented generation systems. Our code is available at https://github.com/ina0105/The-Power-of-Noise-Reproduction.

Key facts. Cited by 1 paper 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 18 of its 29 references that are in the map. First posted on arXiv 3 Jul 2026.

Builds on

18 of 29 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025The Distracting Effect: Understanding Irrelevant Passages in RAG11 May
  2. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models9 Oct
  3. 2024Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models24 Aug
  4. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales19 Jun
  5. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep

Other references · 13

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  6. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  7. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  8. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  9. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  10. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  11. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Promptscited by 218
  12. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
1 more
  1. 2023Evaluating Open-QA Evaluationcited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Contextcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Tackling the Inherent Difficulty of Noise Filtering in RAG
  2. 2025Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems
  3. 2024Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
  4. 2026A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation
  5. 2025Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
  6. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training
  7. 2025On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs
  8. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers