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 LLMs 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 Reinforced Query Reasoner (RQR), a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval. Our approach frames query reformulation as a reinforcement learning problem and employs a novel semi-rule-based reward function. This enables smaller language models, e.g., Qwen2.5-7B-Instruct and Qwen2.5-1.5B-Instruct, to achieve reasoning performance rivaling large-scale LLMs without their prohibitive inference costs. Experiment results on BRIGHT benchmark show that, with BM25 as retrievers, both RQR-7B and RQR-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. All code and dataset will be publicly released.

相关研究指出,用户提交给搜索引擎的查询通常为短查询。由于自然语言本身的特点,短查询通常具有歧义性,同一个查询可以指代不同的事物,或同一事物的不同方面。为了让搜索结果尽可能满足用户多样化的信息需求,搜索引擎需要对返回的结果进行多样化排序,搜索结果多样化技术应运而生。目前已有的基于全局交互的多样化方法通过全连接的自注意力网络捕获全体候选文档间的交互关系,取得了较好的效果。但由于此类方法只考虑文档间的相关关系,并没有考虑到文档是否具有跟查询相关的有效信息,在训练数据有限的条件下效率相对较低。该文提出了一种基于双星型自注意力网络的搜索结果多样化方法,将全连接结构改为星型拓扑结构,并嵌入查询信息以高效率地提取文档跟查询相关的全局交互特征。相关实验结果显示,该模型相对于基于全连接自注意力网络的多样化方法,具备显著的性能优势。