Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Coelho, João, Martins, Bruno, Magalhães, João, Xiong, Chenyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908379060895744
author Coelho, João
Martins, Bruno
Magalhães, João
Xiong, Chenyan
author_facet Coelho, João
Martins, Bruno
Magalhães, João
Xiong, Chenyan
contents Neural retrieval models excel in Web search, but their training requires substantial amounts of labeled query-document pairs, which are costly to obtain. With the widespread availability of Web document collections like ClueWeb22, synthetic queries generated by large language models offer a scalable alternative. Still, synthetic training queries often vary in quality, which leads to suboptimal downstream retrieval performance. Existing methods typically filter out noisy query-document pairs based on signals from an external re-ranker. In contrast, we propose a framework that leverages Direct Preference Optimization (DPO) to integrate ranking signals into the query generation process, aiming to directly optimize the model towards generating high-quality queries that maximize downstream retrieval effectiveness. Experiments show higher ranker-assessed relevance between query-document pairs after DPO, leading to stronger downstream performance on the MS~MARCO benchmark when compared to baseline models trained with synthetic data.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19307
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization
Coelho, João
Martins, Bruno
Magalhães, João
Xiong, Chenyan
Information Retrieval
Neural retrieval models excel in Web search, but their training requires substantial amounts of labeled query-document pairs, which are costly to obtain. With the widespread availability of Web document collections like ClueWeb22, synthetic queries generated by large language models offer a scalable alternative. Still, synthetic training queries often vary in quality, which leads to suboptimal downstream retrieval performance. Existing methods typically filter out noisy query-document pairs based on signals from an external re-ranker. In contrast, we propose a framework that leverages Direct Preference Optimization (DPO) to integrate ranking signals into the query generation process, aiming to directly optimize the model towards generating high-quality queries that maximize downstream retrieval effectiveness. Experiments show higher ranker-assessed relevance between query-document pairs after DPO, leading to stronger downstream performance on the MS~MARCO benchmark when compared to baseline models trained with synthetic data.
title Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization
topic Information Retrieval
url https://arxiv.org/abs/2505.19307