用长上下文大模型一次性重排全部候选段落，提速降耗。
Whole-Pool Setwise Reranking with Long-Context Language Models
- 一次输入所有候选段落，避免重复调用模型
- 双端识别最相关和最不相关段落，50次调用完成100个段落排序
- 适合追求高效精准的检索系统研发人员
以往基于大模型的段落重排方法因输入长度限制，需多次依赖式调用模型，成本高且慢。我们研究近期长上下文大模型如何改变这一局面：当可将全部候选段落一次性输入模型时，无需通过多次局部比较重建排序。为此提出全池集合并行重排（Whole-Pool Setwise Reranking），并设计DualEnd方法，单次调用同时识别最相关与最不相关段落。通过两端协同填充排序，仅用50次串行调用即可完成100个候选段落的排序，相较同类逐段重排方法减少近1次调用。在两个段落重排基准上，使用九个开源大模型进行实验，评估效果、调用次数、令牌消耗、运行时间和输出可靠性，结果表明长上下文不仅是更宽的提示空间，更是实现高效且有效重排的契机。
原文摘要 · Abstract (English)
Previous LLM-based passage re-rankers are often expensive and slow because the input context constraints require the LLM to make many dependent model calls. We study how recent long-context LLMs change this problem: when the full set of retrieved candidate passages can be shown to the model at once, ranking no longer has to be reconstructed from many overlapping local comparisons. We propose Whole-Pool Setwise re-ranking, where each call considers all currently unranked candidate passages, and introduce DualEnd, which identifies both the most and least relevant passages in one call. By filling the ranking from both ends, DualEnd ranks 100 candidates with 50 serial LLM calls, compared with 99 calls for comparable one-passage-at-a-time whole-pool methods. Experiments with nine open-weight LLMs on two passage re-ranking benchmarks, measuring effectiveness, call count, token use, runtime, and output reliability shows that long context is not merely more prompt space, but an opportunity to make LLM re-rankers both effective and efficient.
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。