Mitigating Bias in RAG: Controlling the Embedder

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Taeyoun, Springer, Jacob, Raghunathan, Aditi, Sap, Maarten
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915170280800256
author Kim, Taeyoun
Springer, Jacob
Raghunathan, Aditi
Sap, Maarten
author_facet Kim, Taeyoun
Springer, Jacob
Raghunathan, Aditi
Sap, Maarten
contents In retrieval augmented generation (RAG) systems, each individual component -- the LLM, embedder, and corpus -- could introduce biases in the form of skews towards outputting certain perspectives or identities. In this work, we study the conflict between biases of each component and their relationship to the overall bias of the RAG system, which we call bias conflict. Examining both gender and political biases as case studies, we show that bias conflict can be characterized through a linear relationship among components despite its complexity in 6 different LLMs. Through comprehensive fine-tuning experiments creating 120 differently biased embedders, we demonstrate how to control bias while maintaining utility and reveal the importance of reverse-biasing the embedder to mitigate bias in the overall system. Additionally, we find that LLMs and tasks exhibit varying sensitivities to the embedder bias, a crucial factor to consider for debiasing. Our results underscore that a fair RAG system can be better achieved by carefully controlling the bias of the embedder rather than increasing its fairness.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17390
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mitigating Bias in RAG: Controlling the Embedder
Kim, Taeyoun
Springer, Jacob
Raghunathan, Aditi
Sap, Maarten
Computation and Language
Machine Learning
In retrieval augmented generation (RAG) systems, each individual component -- the LLM, embedder, and corpus -- could introduce biases in the form of skews towards outputting certain perspectives or identities. In this work, we study the conflict between biases of each component and their relationship to the overall bias of the RAG system, which we call bias conflict. Examining both gender and political biases as case studies, we show that bias conflict can be characterized through a linear relationship among components despite its complexity in 6 different LLMs. Through comprehensive fine-tuning experiments creating 120 differently biased embedders, we demonstrate how to control bias while maintaining utility and reveal the importance of reverse-biasing the embedder to mitigate bias in the overall system. Additionally, we find that LLMs and tasks exhibit varying sensitivities to the embedder bias, a crucial factor to consider for debiasing. Our results underscore that a fair RAG system can be better achieved by carefully controlling the bias of the embedder rather than increasing its fairness.
title Mitigating Bias in RAG: Controlling the Embedder
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2502.17390