Work

QueStER: Query Specification for Generative Keyword-Based Retrieval

Year: 2026

Type: conference-paper

Abstract: Generative retrieval (GR) differs from the traditional index-then-retrieve pipeline by storing relevance in model parameters and generating retrieval cues directly from the query, but it can be brittle out of domain and expensive to scale.We introduce QUESTER (QUEry SpecificaTion gEnerative Keyword-Based Retrieval), which bridges GR and query reformulation by learning to generate explicit keyword-based search specifications.Given a user query, a lightweight LLM produces a keyword query that is executed by a standard retriever (BM25), combining the generalization benefits of generative query rewriting with the efficiency and scalability of lexical indexing.We train the rewriting policy with reinforcement learning techniques.Across in-and outof-domain evaluations, QueStER consistently improves over BM25 and is competitive with neural IR baselines, while maintaining strong efficiency. 1

Source: Findings of the Association for Computational Linguistics: EACL

DOI: 10.18653/v1/2026.findings-eacl.312

Authors: Arthur Satouf, Yuxuan Zong, Habiboulaye Amadou Boubacar, Pablo Piantanida, Benjamin Piwowarski