Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918503544520704 |
|---|---|
| author | Zhao, Yingqi Efthymiou, Vasilis Nummenmaa, Jyrki Stefanidis, Kostas |
| author_facet | Zhao, Yingqi Efthymiou, Vasilis Nummenmaa, Jyrki Stefanidis, Kostas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15790 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation Zhao, Yingqi Efthymiou, Vasilis Nummenmaa, Jyrki Stefanidis, Kostas Databases Information Retrieval 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. |
| title | Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation |
| topic | Databases Information Retrieval |
| url | https://arxiv.org/abs/2605.15790 |