Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation
For developers of RAG systems, this work provides a principled method to control bias introduced by retrieval, but the results are incremental as they demonstrate effectiveness without reporting concrete performance numbers.
The paper addresses bias propagation in retrieval-augmented generation (RAG) systems and proposes a fairness-aware retrieval framework (FARO) that balances relevance and fairness. Experimental results show effective mitigation of generation bias while preserving relevance.
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.