用摘要压缩长文档，让模型更高效地排序。
SumRank: Aligning Summarization Models for Long-Document Listwise Reranking
- 先生成精炼摘要，再做整体排序，提升效率。
- 在5个TREC数据集上达到顶尖排序效果。
- 适合需要快速处理长文档的检索系统。
大型语言模型在列表级段落重排序任务中表现优异。然而，直接用于长文档排序会因上下文长度激增而带来效果与效率问题。为此，我们提出一种点式摘要模型SumRank，该模型在下游列表级重排序任务中对齐，将长文档压缩为简洁的、与排序目标一致的摘要，再进行最终排序。SumRank通过三阶段训练流程构建：冷启动监督微调（SFT）、专用强化学习数据构造，以及基于强化学习的排序驱动对齐。该范式使SumRank与下游排序目标对齐，有效保留相关性信号。我们在TREC深度学习赛道（TREC DL 19-23）的五个基准数据集上进行了广泛实验。结果表明，我们的轻量级SumRank模型在显著降低摘要开销和重排序复杂度的同时，实现了最先进的排序性能。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated superior performance in listwise passage reranking task. However, directly applying them to rank long-form documents introduces both effectiveness and efficiency issues due to the substantially increased context length. To address this challenge, we propose a pointwise summarization model SumRank, aligned with downstream listwise reranking, to compress long-form documents into concise rank-aligned summaries before the final listwise reranking stage. To obtain our summarization model SumRank, we introduce a three-stage training pipeline comprising cold-start Supervised Fine-Tuning (SFT), specialized RL data construction, and rank-driven alignment via Reinforcement Learning. This paradigm aligns the SumRank with downstream ranking objectives to preserve relevance signals. We conduct extensive experiments on five benchmark datasets from the TREC Deep Learning tracks (TREC DL 19-23). Results show that our lightweight SumRank model achieves state-of-the-art (SOTA) ranking performance while significantly improving efficiency by reducing both summarization overhead and reranking complexity.
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。