ProRank：通过强化学习进行小语言模型的提示预热以实现文档重排序
ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
AI总结：
本文提出ProRank方法，通过强化学习提升小语言模型对任务提示的理解，结合细粒度分数学习增强表示能力，实验证明其在文档重排序任务中优于现有模型，尤其在BEIR基准上表现突出。
摘要：
重排序是信息检索和检索增强生成的核心任务，近年来大语言模型（LLMs）显著提升了重排序质量。大多数现有工作依赖大规模LLMs（>7B参数），导致计算成本高。小语言模型（SLMs）因其计算效率成为有前景的替代方案。然而，我们的初步定量分析揭示了SLMs的关键局限：其表示空间狭窄，导致表达能力下降，且在未微调的情况下难以理解任务提示。为解决这些问题，我们引入了一种新的两阶段训练方法ProRank，用于基于SLMs的文档重排序。我们提出利用强化学习来提升对任务提示的理解。此外，我们引入细粒度分数学习以增强表示表达性，并进一步提高文档重排序质量。大量实验表明，ProRank在文档重排序任务中始终优于最先进的开源和专有重排序模型。值得注意的是，我们的0.5B ProRank在BEIR基准上甚至超过了强大的LLM重排序模型，证明了经过适当训练的SLMs可以在保持计算效率的同时实现更优的文档重排序性能。
英文摘要：
Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters), presenting high computational costs. Small Language Models (SLMs) offer a promising alternative because of computational efficiency. However, our preliminary quantitative analysis reveals key limitations of SLMs: their representation space is narrow, leading to reduced expressiveness, and they struggle with understanding task prompts without fine-tuning. To address these issues, we introduce a novel two-stage training approach, ProRank, for SLM-based document reranking. We propose using reinforcement learning to improve the understanding of task prompts. Additionally, we introduce fine-grained score learning to enhance representation expressiveness and further improve document reranking quality. Extensive experiments suggest that ProRank consistently outperforms both the most advanced open-source and proprietary reranking models. Notably, our 0.5B ProRank even surpasses powerful LLM reranking models on the BEIR benchmark, establishing that properly trained SLMs can achieve superior document reranking performance while maintaining computational efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
