用概率模型提升大模型文档重排序的稳定性和效率
REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
- 将大模型相关性输出建模为高斯分布，通过递归贝叶斯更新优化
- 相比顶尖方法，NDCG@10提升0.7-11.9，推理次数减少23.4%-84.4%
- 适合需要高效低延迟重排序的现代信息检索系统
大型语言模型（LLMs）在文档重排序这一现代信息检索（IR）系统关键组件中展现出强大能力。然而，现有基于LLM的方法存在排名不确定性、top-k结果不稳定以及因提示词令牌密集导致的高令牌开销等显著局限。为此，我们提出REALM，一种面向不确定性的重排序框架，将LLM生成的相关性建模为高斯分布，并通过递归贝叶斯更新进行精炼。该方法显式捕捉不确定性并最小化冗余查询，在提升排序质量的同时更高效。实验表明，REALM超越现有最优重排序器，显著降低令牌使用量与延迟，使NDCG@10提升0.7–11.9，同时将LLM推理次数减少23.4%–84.4%，可作为新一代重排序器用于现代信息检索系统。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking uncertainty, unstable top-k recovery, and high token cost due to token-intensive prompting. To effectively address these limitations, we propose REALM, an uncertainty-aware re-ranking framework that models LLM-derived relevance as Gaussian distributions and refines them through recursive Bayesian updates. By explicitly capturing uncertainty and minimizing redundant queries, REALM achieves better rankings more efficiently. Experimental results demonstrate that our REALM surpasses state-of-the-art re-rankers while significantly reducing token usage and latency, improving NDCG@10 by 0.7-11.9 and simultaneously reducing the number of LLM inferences by 23.4-84.4%, promoting it as the next-generation re-ranker for modern IR systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。