Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation
On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval
Abstract (arXiv)
Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs. This issue is particularly challenging in top-k settings, where multiple documents jointly influence generation. We propose a fairness-aware retrieval framework that models and controls this bias. Our approach combines controlled bias injection via reranking, a position-aware model of bias propagation, and an optimization formulation that balances relevance and fairness. We further introduce a scalable solution based on Quadratic Fairness via Dual Hyperplane Approximation (FARO), which enables efficient optimization through problem decomposition. Experimental results show that our method effectively mitigates generation bias while preserving relevance. This work provides a principled approach for fairness-aware retrieval in RAG systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 31 references that are in the map. First posted on arXiv 15 May 2026.
Builds on
23 of 31 references.
Closest ancestors · 5
Same direction, newest first
- 2026Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias25 Mar
- 2025Evaluating the Effect of Retrieval Augmentation on Social Biases24 Feb
- 2025Mitigating Bias in RAG: Controlling the Embedder24 Feb
- 2024Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems29 Sep
- 2024Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation17 Sep
Other references · 18
- 2017Attention Is All You Needcited by 60,361
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2020Scaling Laws for Neural Language Modelscited by 6,586
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
- 2022Survey of Hallucination in Natural Language Generationcited by 2,075
- 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
- 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
- 2023Bias and Fairness in Large Language Models: A Surveycited by 639
- 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 286
- 2018Fairness of Exposure in Rankingscited by 190
- 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
6 more
- 2017FA*IR: A Fair Top-k Ranking Algorithmcited by 113
- 2019Policy Learning for Fairness in Rankingcited by 74
- 2021Fairness in Rankings and Recommendations: An Overviewcited by 62
- 2018Reducing Disparate Exposure in Ranking: A Learning To Rank Approachcited by 33
- 2024On the Relationship between Truth and Political Bias in Language Modelscited by 31
- 2024A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directionscited by 27
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
- 2024RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
- 2026Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem
- 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
- 2026Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG
- 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation
- 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAG
- 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning