Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Salemi, Alireza, Zamani, Hamed
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912450074378240
author Salemi, Alireza
Zamani, Hamed
author_facet Salemi, Alireza
Zamani, Hamed
contents This paper investigates the design of a unified search engine to serve multiple retrieval-augmented generation (RAG) agents, each with a distinct task, backbone large language model (LLM), and RAG strategy. We introduce an iterative approach where the search engine generates retrieval results for the RAG agents and gathers feedback on the quality of the retrieved documents during an offline phase. This feedback is then used to iteratively optimize the search engine using an expectation-maximization algorithm, with the goal of maximizing each agent's utility function. Additionally, we adapt this to an online setting, allowing the search engine to refine its behavior based on real-time individual agents feedback to better serve the results for each of them. Experiments on datasets from the Knowledge-Intensive Language Tasks (KILT) benchmark demonstrates that our approach significantly on average outperforms baselines across 18 RAG models. We demonstrate that our method effectively ``personalizes'' the retrieval for each RAG agent based on the collected feedback. Finally, we provide a comprehensive ablation study to explore various aspects of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization
Salemi, Alireza
Zamani, Hamed
Computation and Language
Information Retrieval
This paper investigates the design of a unified search engine to serve multiple retrieval-augmented generation (RAG) agents, each with a distinct task, backbone large language model (LLM), and RAG strategy. We introduce an iterative approach where the search engine generates retrieval results for the RAG agents and gathers feedback on the quality of the retrieved documents during an offline phase. This feedback is then used to iteratively optimize the search engine using an expectation-maximization algorithm, with the goal of maximizing each agent's utility function. Additionally, we adapt this to an online setting, allowing the search engine to refine its behavior based on real-time individual agents feedback to better serve the results for each of them. Experiments on datasets from the Knowledge-Intensive Language Tasks (KILT) benchmark demonstrates that our approach significantly on average outperforms baselines across 18 RAG models. We demonstrate that our method effectively ``personalizes'' the retrieval for each RAG agent based on the collected feedback. Finally, we provide a comprehensive ablation study to explore various aspects of our method.
title Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2410.09942