TongSearch-QR: Reinforced Query Reasoning for Retrieval

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qin, Xubo, Bai, Jun, Li, Jiaqi, Jia, Zixia, Zheng, Zilong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915345810325504
author Qin, Xubo
Bai, Jun
Li, Jiaqi
Jia, Zixia
Zheng, Zilong
author_facet Qin, Xubo
Bai, Jun
Li, Jiaqi
Jia, Zixia
Zheng, Zilong
contents Traditional information retrieval (IR) methods excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks that require multi-hop inference or complex semantic understanding between queries and documents. One promising solution is to explicitly rewrite or augment queries using large language models (LLMs) to elicit reasoning-relevant content prior to retrieval. However, the widespread use of large-scale language models like GPT-4 or LLaMA3-70B remains impractical due to their high inference cost and limited deployability in real-world systems. In this work, we introduce TongSearch QR (Previously Known as "TongSearch Reasoner"), a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval. With a novel semi-rule-based reward function, we employ reinforcement learning approaches enabling smaller language models, e,g, Qwen2.5-7B-Instruct and Qwen2.5-1.5B-Instruct, to achieve query reasoning performance rivaling large-scale language models without their prohibitive inference costs. Experiment results on BRIGHT benchmark show that with BM25 as retrievers, both TongSearch QR-7B and TongSearch QR-1.5B models significantly outperform existing baselines, including prompt-based query reasoners and some latest dense retrievers trained for reasoning-intensive retrieval tasks, offering superior adaptability for real-world deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11603
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TongSearch-QR: Reinforced Query Reasoning for Retrieval
Qin, Xubo
Bai, Jun
Li, Jiaqi
Jia, Zixia
Zheng, Zilong
Information Retrieval
Traditional information retrieval (IR) methods excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks that require multi-hop inference or complex semantic understanding between queries and documents. One promising solution is to explicitly rewrite or augment queries using large language models (LLMs) to elicit reasoning-relevant content prior to retrieval. However, the widespread use of large-scale language models like GPT-4 or LLaMA3-70B remains impractical due to their high inference cost and limited deployability in real-world systems. In this work, we introduce TongSearch QR (Previously Known as "TongSearch Reasoner"), a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval. With a novel semi-rule-based reward function, we employ reinforcement learning approaches enabling smaller language models, e,g, Qwen2.5-7B-Instruct and Qwen2.5-1.5B-Instruct, to achieve query reasoning performance rivaling large-scale language models without their prohibitive inference costs. Experiment results on BRIGHT benchmark show that with BM25 as retrievers, both TongSearch QR-7B and TongSearch QR-1.5B models significantly outperform existing baselines, including prompt-based query reasoners and some latest dense retrievers trained for reasoning-intensive retrieval tasks, offering superior adaptability for real-world deployment.
title TongSearch-QR: Reinforced Query Reasoning for Retrieval
topic Information Retrieval
url https://arxiv.org/abs/2506.11603