mlsanityData to 14 Oct 2026

Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering

arXiv 2404.10496 ↗First posted 16 Apr 2024cs.IRcited by 5

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

Abstract (arXiv)

The practice of Retrieval-Augmented Generation (RAG), which integrates Large Language Models (LLMs) with retrieval systems, has become increasingly prevalent. However, the repercussions of LLM-derived content infiltrating the web and influencing the retrieval-generation feedback loop are largely uncharted territories. In this study, we construct and iteratively run a simulation pipeline to deeply investigate the short-term and long-term effects of LLM text on RAG systems. Taking the trending Open Domain Question Answering (ODQA) task as a point of entry, our findings reveal a potential digital "Spiral of Silence" effect, with LLM-generated text consistently outperforming human-authored content in search rankings, thereby diminishing the presence and impact of human contributions online. This trend risks creating an imbalanced information ecosystem, where the unchecked proliferation of erroneous LLM-generated content may result in the marginalization of accurate information. We urge the academic community to take heed of this potential issue, ensuring a diverse and authentic digital information landscape.

Key facts. Cited by 5 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 34 of its 60 references that are in the map. First posted on arXiv 16 Apr 2024.

Builds on

34 of 60 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep

Other references · 33

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  7. 2017Billion-scale similarity search with GPUscited by 2,497
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  9. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  11. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  12. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
21 more
  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  4. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  5. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 491
  6. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 451
  7. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  8. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 356
  9. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  10. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  11. 2023Self-Consuming Generative Models Go MADcited by 250
  12. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
  13. 2023Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigationscited by 158
  14. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 151
  15. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  16. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 128
  17. 2019Degenerate Feedback Loops in Recommender Systemscited by 67
  18. 2018Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memorycited by 49
  19. 2023Neural Retrievers are Biased Towards LLM-Generated Contentcited by 38
  20. 2021A Survey on Echo Chambers on Social Media: Description, Detection and Mitigationcited by 12
  21. 2023Domain Incremental Lifelong Learning in an Open Worldcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2024ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generatorcited by 19
  2. 2025LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendationcited by 19
  3. 2025Political Ideology Shifts in Large Language Modelscited by 5
  4. 2026Retrieval Collapses When AI Pollutes the Webcited by 4
  5. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Pipelines: A Fundamental Study on the Rise of Generative-Retrieval Architectures in Web Research
  2. 2025Evaluating the Retrieval Robustness of Large Language Models
  3. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  4. 2025On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems
  5. 2024Deploying Large Language Models With Retrieval Augmented Generation
  6. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
  7. 2025Out of Style: RAG's Fragility to Linguistic Variation
  8. 2024DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation