Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG

• URL: http://arxiv.org/abs/2604.06097v1
• Date: Tue, 07 Apr 2026 17:10:15 GMT
• Title: Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG
• Abstract summary: 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.
• Score: 20.162803360845462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biases -- including brevity, position, literal matching, and repetition biases -- that can compromise retrieval quality. Query rewriting techniques are now standard in RAG pipelines, yet their impact on these biases remains unexplored. We present the first systematic study of how query enhancement techniques affect dense retrieval biases, evaluating five methods across six retrievers. Our findings reveal that simple LLM-based rewriting achieves the strongest aggregate bias reduction (54\%), yet fails under adversarial conditions where multiple biases combine. Mechanistic analysis uncovers two distinct mechanisms: simple rewriting reduces bias through increased score variance, while pseudo-document generation methods achieve reduction through genuine decorrelation from bias-inducing features. However, no technique uniformly addresses all biases, and effects vary substantially across retrievers. Our results provide practical guidance for selecting query enhancement strategies based on specific bias vulnerabilities. More broadly, we establish a taxonomy distinguishing query-document interaction biases from document encoding biases, clarifying the limits of query-side interventions for debiasing RAG systems.

Related papers

• Lost in the Evidence? Reproducing Document Position and Context Size Effects in RAG [3.597778914286147]
  Retrieval-Augmented Generation (RAG) systems rely on retrieved documents being input to a model's input context.<n>Prior work reports position-based effects such as lost in the middle and related long-context phenomena.<n>We show that topic sampling is a major source of variance: small topic sets can exaggerate ordering effects.<n>We also study a more realistic RAG scenario in which relevance is mediated by a retriever rather than oracle access to ground-truth documents.
  arXiv  Detail & Related papers  (2026-05-26T14:44:19Z)
• Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems [55.04168927059962]
  Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity.<n>We introduce BRIGHT-Pro, an expert-annotated benchmark that expands each query with multi-aspect gold evidence.<n>We also construct RTriever- Synth, an aspect-decomposed synthetic corpus that generates complementary positives and positive-conditioned hard negatives.
  arXiv  Detail & Related papers  (2026-05-05T17:42:50Z)
• R$^3$AG: Retriever Routing for Retrieval-Augmented Generation [59.47703698994575]
  R$3$AG decomposes retriever capability into two learnable dimensions: retrieval quality and generation utility.<n>R$3$AG consistently outperforms both the best individual retrievers and state-of-the-art static routing methods.
  arXiv  Detail & Related papers  (2026-04-22T06:51:20Z)
• 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)
• Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy [0.0]
  We present a systematic literature review of bias mitigation methods.<n>They explicitly consider AI feedback loops and are validated in multi-round simulations or live A/B tests.<n>Each study is coded on six dimensions: mitigation technique, biases addressed, dynamic testing set-up, evaluation focus, application domain, and ML task, organising them into a reusable taxonomy.
  arXiv  Detail & Related papers  (2025-08-28T09:12:38Z)
• 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)
• 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)
• Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence [56.09494651178128]
  Retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG)<n>We quantify the impact of biases, such as a preference for shorter documents, on retrievers like Dragon+ and Contriever.<n>We uncover major vulnerabilities, showing retrievers favor shorter documents, early positions, repeated entities, and literal matches, all while ignoring the answer's presence!
  arXiv  Detail & Related papers  (2025-03-06T23:23:13Z)
• Rectify the Regression Bias in Long-Tailed Object Detection [29.34827806854778]
  Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss function design, while ignoring the subtle influence of the regression branch. This paper shows that the regression bias exists and does adversely and seriously impact the detection accuracy.
  arXiv  Detail & Related papers  (2024-01-29T04:40:33Z)
• Retrieval Augmentation for Commonsense Reasoning: A Unified Approach [64.63071051375289]
  We propose a unified framework of retrieval-augmented commonsense reasoning (called RACo) Our proposed RACo can significantly outperform other knowledge-enhanced method counterparts.
  arXiv  Detail & Related papers  (2022-10-23T23:49:08Z)
• Information-Theoretic Bias Reduction via Causal View of Spurious Correlation [71.9123886505321]
  We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation. We present a novel debiasing framework against the algorithmic bias, which incorporates a bias regularization loss. The proposed bias measurement and debiasing approaches are validated in diverse realistic scenarios.
  arXiv  Detail & Related papers  (2022-01-10T01:19:31Z)

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.