Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation

TL;DR

This paper introduces a fairness-aware retrieval framework for Retrieval-Augmented Generation systems that mitigates bias propagation while maintaining relevance, using a novel optimization approach called FARO.

Contribution

It presents a new framework combining bias control, position-aware modeling, and an efficient optimization method for fairness in RAG retrievals.

Findings

Effectively reduces bias in generated outputs.

Preserves relevance while improving fairness.

Scalable optimization method outperforms baselines.

Abstract

Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs. This issue is particularly challenging in top-k settings, where multiple documents jointly influence generation. We propose a fairness-aware retrieval framework that models and controls this bias. Our approach combines controlled bias injection via reranking, a position-aware model of bias propagation, and an optimization formulation that balances relevance and fairness. We further introduce a scalable solution based on Quadratic Fairness via Dual Hyperplane Approximation (FARO), which enables efficient optimization through problem decomposition. Experimental results show that our method effectively mitigates generation bias while preserving relevance. This work provides a principled approach for fairness-aware retrieval in RAG systems.