使用基于大语言模型的列表式排序器引导检索
Guiding Retrieval using LLM-based Listwise Rankers
AI总结：
针对级联式检索-重排序的有界召回问题，提出适配列表式LLM重排序器的自适应检索方法，通过合并初始排序与反馈文档结果，在推理次数不变的情况下显著提升检索效果。
摘要：
大语言模型（LLM）作为重排序器展现出巨大潜力，尤其是在“列表式”场景中——即通过提示LLM一次性对多个搜索结果进行重排序。然而，这种“级联式”检索-重排序方法受限于有界召回问题：初始检索阶段未被召回的相关文档会被永久排除在最终排序之外。自适应检索技术可解决这一问题，但无法与列表式重排序器配合使用，因为这类技术假设文档的得分是独立于其他文档计算的。本文提出了一种对现有自适应检索方法的改进方案，该方案支持列表式场景，且能够引导检索过程本身（从而克服LLM重排序器的有界召回问题）。具体而言，我们提出的算法会合并初始排序结果，以及截至当前已见过的最相关文档所提供的反馈文档。通过在不同LLM重排序器、第一阶段检索器和反馈来源上开展的大量实验，我们证明该方法可将nDCG@10提升最高13.23%，召回率提升28.02%——同时保持LLM推理总次数不变，且自适应过程带来的开销极低。这项工作为在初始结果池受限的场景（如受遗留系统限制，或受部署语义第一阶段检索器的成本限制）中应用基于LLM的搜索开辟了道路。
英文摘要：
Large Language Models (LLMs) have shown strong promise as rerankers, especially in ``listwise'' settings where an LLM is prompted to rerank several search results at once. However, this ``cascading'' retrieve-and-rerank approach is limited by the bounded recall problem: relevant documents not retrieved initially are permanently excluded from the final ranking. Adaptive retrieval techniques address this problem, but do not work with listwise rerankers because they assume a document's score is computed independently from other documents. In this paper, we propose an adaptation of an existing adaptive retrieval method that supports the listwise setting and helps guide the retrieval process itself (thereby overcoming the bounded recall problem for LLM rerankers). Specifically, our proposed algorithm merges results both from the initial ranking and feedback documents provided by the most relevant documents seen up to that point. Through extensive experiments across diverse LLM rerankers, first stage retrievers, and feedback sources, we demonstrate that our method can improve nDCG@10 by up to 13.23% and recall by 28.02%--all while keeping the total number of LLM inferences constant and overheads due to the adaptive process minimal. The work opens the door to leveraging LLM-based search in settings where the initial pool of results is limited, e.g., by legacy systems, or by the cost of deploying a semantic first-stage.
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。
