Do RAG Systems Suffer From Positional Bias?

• URL: http://arxiv.org/abs/2505.15561v1
• Date: Wed, 21 May 2025 14:18:01 GMT
• Title: Do RAG Systems Suffer From Positional Bias?
• Authors: Florin Cuconasu, Simone Filice, Guy Horowitz, Yoelle Maarek, Fabrizio Silvestri,
• Abstract summary: We show how state-of-the-art retrieval pipelines, while attempting to retrieve relevant passages, systematically bring highly distracting ones to the top ranks.<n>Our findings reveal that sophisticated strategies that attempt to rearrange the passages based on LLM positional preferences do not perform better than random shuffling.
• Score: 13.06567550060387
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval Augmented Generation enhances LLM accuracy by adding passages retrieved from an external corpus to the LLM prompt. This paper investigates how positional bias - the tendency of LLMs to weight information differently based on its position in the prompt - affects not only the LLM's capability to capitalize on relevant passages, but also its susceptibility to distracting passages. Through extensive experiments on three benchmarks, we show how state-of-the-art retrieval pipelines, while attempting to retrieve relevant passages, systematically bring highly distracting ones to the top ranks, with over 60% of queries containing at least one highly distracting passage among the top-10 retrieved passages. As a result, the impact of the LLM positional bias, which in controlled settings is often reported as very prominent by related works, is actually marginal in real scenarios since both relevant and distracting passages are, in turn, penalized. Indeed, our findings reveal that sophisticated strategies that attempt to rearrange the passages based on LLM positional preferences do not perform better than random shuffling.

Related papers

• GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis [30.185213495829164]
  The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs)<n>We propose GainRAG, a novel approach that aligns the retriever's and LLM's preferences by defining a new metric, "gain", which measure how well an input passage contributes to correct outputs.<n>The experimental results on 6 datasets verify the effectiveness of GainRAG.
  arXiv  Detail & Related papers  (2025-05-24T14:14:57Z)
• The Distracting Effect: Understanding Irrelevant Passages in RAG [8.882885336338205]
  We identify and use hard distracting passages to improve RAG systems.<n>We achieve up to a 7.5% increase in answering accuracy compared to counterparts fine-tuned on conventional RAG datasets.<n>Our contribution is two-fold: first, we move beyond the simple binary classification of irrelevant passages as either completely unrelated vs. distracting, and second, we develop and analyze multiple methods for finding hard distracting passages.
  arXiv  Detail & Related papers  (2025-05-11T09:25:05Z)
• The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation [73.16564415490113]
  Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant document from external knowledge sources.<n>We propose two approaches, FairFT and FairFilter, to mitigate the fairness issues introduced by RAG for small-scale LLMs.
  arXiv  Detail & Related papers  (2025-04-11T10:17:10Z)
• Enough Coin Flips Can Make LLMs Act Bayesian [71.79085204454039]
  Large language models (LLMs) exhibit the ability to generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning (ICL)<n>We investigate whether LLMs use ICL to perform structured reasoning in ways that are consistent with a Bayesian framework or rely on pattern matching.
  arXiv  Detail & Related papers  (2025-03-06T18:59:23Z)
• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system.<n>It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• LLMs can be Fooled into Labelling a Document as Relevant (best café near me; this paper is perfectly relevant) [26.996231897558324]
  This work reports on experiments to study the labelling of short texts (i.e., passages) for relevance using multiple open-source and proprietary LLMs.<n>While the overall agreement of some LLMs with human judgements is comparable to human-to-human agreement measured in previous research, LLMs are more likely to label passages as relevant compared to human judges.
  arXiv  Detail & Related papers  (2025-01-29T20:11:35Z)
• Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output [49.893971654861424]
  We present a light-weight approach for detecting nonfactual outputs from retrieval-augmented generation (RAG) We compute a factuality score that can be thresholded to yield a binary decision. Our experiments show high area under the ROC curve (AUC) across a wide range of relevant open source datasets.
  arXiv  Detail & Related papers  (2024-11-01T20:44:59Z)
• FIRST: Faster Improved Listwise Reranking with Single Token Decoding [56.727761901751194]
  First, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
  arXiv  Detail & Related papers  (2024-06-21T21:27:50Z)
• Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs [18.832135309689736]
  Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. Recent studies show a positional bias in LLMs, demonstrating varying performance depending on the location of useful information. We develop a Position-Aware PAPEFT approach which is composed of a data augmentation technique and an efficient parameter adapter.
  arXiv  Detail & Related papers  (2024-04-01T19:04:17Z)
• Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment [32.12998469814097]
  A novel causal prompting method based on front-door adjustment is proposed to effectively mitigate Large Language Models (LLMs) biases.<n> Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets.
  arXiv  Detail & Related papers  (2024-03-05T07:47:34Z)
• The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning [61.68787689234622]
  A recent study, LIMA, shows that using merely 1K examples for alignment tuning can achieve significant alignment performance as well. This raises questions about how exactly the alignment tuning transforms a base LLM. We show that the gap between tuning-free and tuning-based alignment methods can be significantly reduced through strategic prompting.
  arXiv  Detail & Related papers  (2023-12-04T00:46:11Z)

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.