Towards FairRAG: Preventing Representational Harm in Retrieval-Augmented Generation by Enforcing Fair Exposure at Retrieval Time

• URL: http://arxiv.org/abs/2605.18806v1
• Date: Mon, 11 May 2026 22:01:07 GMT
• Title: Towards FairRAG: Preventing Representational Harm in Retrieval-Augmented Generation by Enforcing Fair Exposure at Retrieval Time
• Abstract summary: Retrieval-augmented generation (RAG) is a technique for addressing hallucination.<n>RAG's multi-component pipeline introduces vulnerabilities where biases can be introduced.<n>This study considers two previously developed utility-focused ranking strategies alongside two proposed exposure-aware approaches.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Large Language Model (LLM) integration has accelerated in high-stakes domains, model hallucination is a critical issue. Retrieval-augmented generation (RAG) is a technique for addressing hallucination; however, RAG's multi-component pipeline introduces vulnerabilities where biases can be introduced. This study considers two previously developed utility-focused ranking strategies (Standard and Stochastic) alongside two proposed exposure-aware approaches (Forced-Exposure and Representative Stochastic). Using the TREC 2022 Fair Ranking Dataset, which contains Wikipedia articles annotated as protected or non-protected, the LLM was asked to identify relevant articles with citations for four scenario-based Q&A prompts. The retrieval rankings and the generated outputs were evaluated for exposure bias and utility across all ranking methods. Overall, the Representative Stochastic ranker resulted in a statistically significant near-parity average exposure, acknowledging that relevance scores initially produced during retrieval are already shaped by representational bias, whereas the other rankers assume those scores are unbiased. Across all the methods of document ranking, generation demographic parity closely mirrored the exposure parity, reinforcing that representational bias in RAG systems is driven by retrieval and propagates to generation. These findings highlight that retrieval ranking is a critical point for mitigating downstream bias and propose a Representative Stochastic ranker that reintroduces fairness in RAG systems.

Related papers

• Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery [95.44432473367836]
  Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.<n>We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discnative, and testable hypothesis spaces from inconclusive evidence.<n>We introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets.
  arXiv  Detail & Related papers  (2026-07-17T08:56:43Z)
• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG [20.162803360845462]
  We present the first systematic study of how query enhancement techniques affect dense retrieval biases.<n>Simple rewriting achieves the strongest aggregate bias reduction (54%), yet fails under adversarial conditions where multiple biases combine.<n>Our results provide practical guidance for selecting query enhancement strategies based on specific bias vulnerabilities.
  arXiv  Detail & Related papers  (2026-04-07T17:10:15Z)
• Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts [7.344577590113121]
  Social biases inherent in large language models (LLMs) raise significant fairness concerns.<n>This work focuses on evaluating and understanding the social bias implications of RAG.
  arXiv  Detail & Related papers  (2026-02-10T06:27:56Z)
• Re-Rankers as Relevance Judges [65.37611299805856]
  We reproduce re-rankers in a re-ranker-as-relevance-judge setup.<n>We perform experiments on TREC-DL 2019 to 2023 with 8 re-rankers from 3 families, ranging from 220M to 32B, and analyse the evaluation bias exhibited by re-ranker-based judges.
  arXiv  Detail & Related papers  (2026-01-08T00:02:59Z)
• Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search [18.386455479798574]
  Bias-Guided Prompt Search (BGPS) is a framework that automatically generates prompts that aim to maximize the presence of biases in images.<n>BGPS comprises two components: (1) an LLM instructed to produce attribute-neutral prompts and (2) attribute classifiers acting on the TTI's internal representations.<n>We conduct extensive experiments on Stable Diffusion 1.5 and a state-of-the-art debiased model and discover an array of subtle and previously undocumented biases.
  arXiv  Detail & Related papers  (2025-12-09T15:39:04Z)
• T-Retrievability: A Topic-Focused Approach to Measure Fair Document Exposure in Information Retrieval [22.953432572278597]
  We propose a topic-focused localised retrievability measure, which first computes retrievability scores over multiple groups of topically-related documents.<n>Our analysis uncovers new insights into the exposure characteristics of various neural ranking models.
  arXiv  Detail & Related papers  (2025-08-29T15:14:16Z)
• Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents [64.43980129731587]
  We propose a causal-inspired inference-time debiasing method called Causal Diagnosis and Correction (CDC)<n>CDC first diagnoses the bias effect of the perplexity and then separates the bias effect from the overall relevance score.<n> Experimental results across three domains demonstrate the superior debiasing effectiveness.
  arXiv  Detail & Related papers  (2025-03-11T17:59:00Z)
• 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)
• Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations [63.52709761339949]
  We first contribute a dedicated dataset called the Fair Forgery Detection (FairFD) dataset, where we prove the racial bias of public state-of-the-art (SOTA) methods.<n>We design novel metrics including Approach Averaged Metric and Utility Regularized Metric, which can avoid deceptive results.<n>We also present an effective and robust post-processing technique, Bias Pruning with Fair Activations (BPFA), which improves fairness without requiring retraining or weight updates.
  arXiv  Detail & Related papers  (2024-07-19T14:53:18Z)
• Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers [9.811131801693856]
  We provide a novel framework to measure the fairness in the retrieved text contents of ranking models. We propose an adversarial bias mitigation approach applied to the state-of-the-art Bert rankers. Our results on the MS MARCO benchmark show that, while the fairness of all ranking models is lower than the ones of ranker-agnostic baselines, the fairness in retrieved contents significantly improves when applying the proposed adversarial training.
  arXiv  Detail & Related papers  (2021-04-28T08:53:54Z)

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.