重新排序前三思：多视角证据与推理融合用于文本重排序

中文摘要 AI 辅助

基于大语言模型（LLM）的推理式重排序在文本排序中展现出显著的改进效果。然而，当前方法主要依赖单一推理轨迹，导致排序结果易受推理错误影响，并且在建模文档相关性背后的多面信号方面存在固有局限。为解决这一困境，我们提出了MERIT-Rank（多视角证据与推理融合用于文本重排序），一个通过建模互补推理轨迹来提升重排序鲁棒性的框架。MERIT-Rank构建了多轨迹推理空间（MTRS），从多个视角评估查询-文档相关性，并引入一个联合重排序器，将这些推理路径整合为统一的排序决策。我们进一步开发了渐进式排序策略优化（PRPO），一种渐进式训练框架，通过分阶段优化目标稳定推理轨迹并持续提升排序质量。在推理密集型与传统检索基准上的实验表明，MERIT-Rank持续优于竞争基线。值得注意的是，4B模型在BRIGHT基准上显著超越了大多数7B甚至32B的重排序器。

英文摘要

Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single reasoning trajectory, resulting in rankings that are susceptible to reasoning errors and inherently constrained in modeling the multifaceted signals underlying document relevance. To resolve this dilemma, we propose MERIT-Rank(Multi-perspective Evidence and Reasoning Integration for Text Reranking), a framework that models complementary reasoning trajectories to improve reranking robustness. MERIT-Rank formulates a Multi-Trajectory Reasoning Space (MTRS) that evaluates query-document relevance from multiple perspectives and introduces a joint reranker that consolidates these reasoning paths into a unified ranking decision. We further develop Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes reasoning trajectories while continually improving ranking quality through staged optimization objectives. Experiments on both reasoning-intensive and traditional retrieval benchmarks show that MERIT-Rank consistently achieves superior performance over competitive baselines. The 4B model notably outperforms most 7B and even 32B rerankers on BRIGHT.

发表机构

• Honor Device Co., Ltd（荣耀终端有限公司）

机构由 AI 辅助整理，请以论文原文为准。