mlsanityData to 14 Oct 2026

Mitigating Bias in RAG: Controlling the Embedder

arXiv 2502.17390 ↗First posted 24 Feb 2025cs.CL cs.LGcited by 6

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

Abstract (arXiv)

In retrieval augmented generation (RAG) systems, each individual component -- the LLM, embedder, and corpus -- could introduce biases in the form of skews towards outputting certain perspectives or identities. In this work, we study the conflict between biases of each component and their relationship to the overall bias of the RAG system, which we call bias conflict. Examining both gender and political biases as case studies, we show that bias conflict can be characterized through a linear relationship among components despite its complexity in 6 different LLMs. Through comprehensive fine-tuning experiments creating 120 differently biased embedders, we demonstrate how to control bias while maintaining utility and reveal the importance of reverse-biasing the embedder to mitigate bias in the overall system. Additionally, we find that LLMs and tasks exhibit varying sensitivities to the embedder bias, a crucial factor to consider for debiasing. Our results underscore that a fair RAG system can be better achieved by carefully controlling the bias of the embedder rather than increasing its fairness.

Key facts. Cited by 6 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 42 of its 64 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

42 of 64 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users10 Oct
  2. 2024Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems29 Sep
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 39

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  7. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  9. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  11. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  12. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
27 more
  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  2. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  3. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  4. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  5. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  6. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  7. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 430
  8. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  9. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  10. 2018Gender Bias in Neural Natural Language Processingcited by 211
  11. 2019Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphologycited by 200
  12. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 144
  13. 2023Understanding Catastrophic Forgetting in Language Models via Implicit Inferencecited by 144
  14. 2020We Can Detect Your Bias: Predicting the Political Ideology of News Articlescited by 92
  15. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 42
  16. 2024FairRAG: Fair Human Generation via Fair Retrieval Augmentationcited by 34
  17. 2024Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Modelscited by 33
  18. 2024On the Relationship between Truth and Political Bias in Language Modelscited by 31
  19. 2020Do Neural Ranking Models Intensify Gender Bias?cited by 29
  20. 2024Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximizationcited by 29
  21. 2017Quantifying Search Bias: Investigating Sources of Bias for Political Searches in Social Mediacited by 18
  22. 2021Generating Informative Conclusions for Argumentative Textscited by 14
  23. 2024Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awarenesscited by 12
  24. 2024Quantifying Generative Media Bias with a Corpus of Real-world and Generated News Articlescited by 9
  25. 2024Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Textcited by 8
  26. 2024Efficient and Versatile Robust Fine-Tuning of Zero-shot Modelscited by 7
  27. 2024A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directionscited by 31
  2. 2025Out of Style: RAG's Fragility to Linguistic Variationcited by 11
  3. 2025Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMscited by 8
  4. 2026The Impact of Ideological Discourses in RAG: A Case Study with COVID-19 Treatmentscited by 1
  5. 2025Quantifying Document Impact in RAG-LLMscited by 0
  6. 2026Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts
  2. 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
  3. 2025Evaluating the Effect of Retrieval Augmentation on Social Biases
  4. 2026Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG
  5. 2025Do RAG Systems Really Suffer From Positional Bias?
  6. 2026Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
  7. 2024Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation
  8. 2026DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation