Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias

• URL: http://arxiv.org/abs/2603.24218v1
• Date: Wed, 25 Mar 2026 11:45:52 GMT
• Title: Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias
• Abstract summary: Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have achieved substantial improvements in accuracy.<n>We investigate the impact of three key factors on query group fairness in RAG.
• Score: 3.874524858753285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have achieved substantial improvements in accuracy by grounding their responses in external documents that are relevant to the user's query. However, relatively little work has investigated the impact of RAG in terms of fairness. Particularly, it is not yet known if queries that are associated with certain groups within a fairness category systematically receive higher accuracy, or accuracy improvements in RAG systems compared to LLM-only, a phenomenon we refer to as query group fairness. In this work, we conduct extensive experiments to investigate the impact of three key factors on query group fairness in RAG, namely: Group exposure, i.e., the proportion of documents from each group appearing in the retrieved set, determined by the retriever; Group utility, i.e., the degree to which documents from each group contribute to improving answer accuracy, capturing retriever-generator interactions; and Group attribution, i.e., the extent to which the generator relies on documents from each group when producing responses. We examine group-level average accuracy and accuracy improvements disparities across four fairness categories using three datasets derived from the TREC 2022 Fair Ranking Track for two tasks: article generation and title generation. Our findings show that RAG systems suffer from the query group fairness problem and amplify disparities in terms of average accuracy across queries from different groups, compared to an LLM-only setting. Moreover, group utility, exposure, and attribution can exhibit strong positive or negative correlations with average accuracy or accuracy improvements of queries from that group, highlighting their important role in fair RAG. Our data and code are publicly available from Github.

Related papers

• Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction [2.6365690297272617]
  The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks.<n>We propose a training-free, inference-only Retrieval Augmented Generation (RAG) based framework that leverages diversity-aware masking to identify erroneous claims.<n>We further introduce M$$C$+$, an ensemble-based framework that combines corrections across multiple rankers to reduce retrieval bias and improve robustness.
  arXiv  Detail & Related papers  (2026-04-21T14:13:07Z)
• GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning [26.616849067985967]
  Groupwise is a novel reranking paradigm for large language models.<n>We propose an innovative pipeline for high quality retrieval and ranking data.<n>The resulting data can be leveraged not only for training the reranker but also for training the retriever.
  arXiv  Detail & Related papers  (2025-11-10T15:25:31Z)
• LTRR: Learning To Rank Retrievers for LLMs [53.285436927963865]
  We show that routing-based RAG systems can outperform the best single-retriever-based systems.<n>Performance gains are especially pronounced in models trained with the Answer Correctness (AC) metric.<n>As part of the SIGIR 2025 LiveRAG challenge, our submitted system demonstrated the practical viability of our approach.
  arXiv  Detail & Related papers  (2025-06-16T17:53:18Z)
• Quantifying Query Fairness Under Unawareness [82.33181164973365]
  We introduce a robust fairness estimator based on quantification that effectively handles multiple sensitive attributes beyond binary classifications.<n>Our method outperforms existing baselines across various sensitive attributes and is the first to establish a reliable protocol for measuring fairness under unawareness.
  arXiv  Detail & Related papers  (2025-06-04T16:31:44Z)
• Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness [61.45587642780908]
  We propose a three-step approach for parameter-efficient fine-tuning of image-text foundation models.<n>Our method improves its two key components: minority samples identification and the robust training algorithm.<n>Our theoretical analysis shows that our PPA enhances minority group identification and is Bayes optimal for minimizing the balanced group error.
  arXiv  Detail & Related papers  (2025-03-12T15:46:12Z)
• Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems [18.926129063000264]
  We aim to empirically evaluate fairness in several Retrieval-Augmented Generation (RAG) methods.<n>Our experimental results indicate that, despite recent advances in utility-driven optimization, fairness issues persist in both the retrieval and generation stages.<n>These findings underscore the need for targeted interventions to address fairness concerns throughout the RAG pipeline.
  arXiv  Detail & Related papers  (2024-09-29T22:04:26Z)
• Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation [53.285436927963865]
  This paper is the first systematic evaluation of RAG systems that integrate fairness-aware rankings.<n>We show that incorporating fairness-aware retrieval often maintains or even enhances both ranking quality and generation quality.
  arXiv  Detail & Related papers  (2024-09-17T23:10:04Z)
• Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers [0.0]
  Retrieval-Augmented Generation (RAG) is a prevalent approach to infuse a private knowledge base of documents with Large Language Models (LLM) to build Generative Q&A (Question-Answering) systems. We propose the 'Blended RAG' method of leveraging semantic search techniques, such as Vector indexes and Sparse indexes, blended with hybrid query strategies. Our study achieves better retrieval results and sets new benchmarks for IR (Information Retrieval) datasets like NQ and TREC-COVID datasets.
  arXiv  Detail & Related papers  (2024-03-22T17:13:46Z)
• AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization [109.91265884632239]
  Group distributionally robust optimization (G-DRO) can minimize the worst-case loss over a set of pre-defined groups over training data. We propose AGRO -- Adversarial Group discovery for Distributionally Robust Optimization. AGRO results in 8% higher model performance on average on known worst-groups, compared to prior group discovery approaches.
  arXiv  Detail & Related papers  (2022-12-02T00:57:03Z)
• Towards Group Robustness in the presence of Partial Group Labels [61.33713547766866]
  spurious correlations between input samples and the target labels wrongly direct the neural network predictions. We propose an algorithm that optimize for the worst-off group assignments from a constraint set. We show improvements in the minority group's performance while preserving overall aggregate accuracy across groups.
  arXiv  Detail & Related papers  (2022-01-10T22:04:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.