首次揭示交叉编码器重排序的缩放规律，可预测大模型性能。
Scaling Laws for Cross-Encoder Reranking
- 基于点、对、列表三种目标研究重排序模型缩放规律。
- 用150M模型准确预测400M和1B模型在MSMARCO和TREC上的表现。
- 发现数据量扩大比模型变大更有利于检索效果，适合工业级系统设计。
语言模型和第一阶段检索的缩放规律已被广泛研究，但重排序领域尚无系统性工作。本文首次系统研究了跨编码器重排序器在点式、对式和列表式目标下的缩放规律。在模型规模与训练投入变化下，排名质量遵循可预测的幂律关系，使得可通过小规模实验预估大规模模型性能。我们使用最大150M参数的模型，在MSMARCO-dev和TREC DL数据集上成功预测了400M和1B参数重排序器的表现。除预测外，基于拟合的联合缩放规律推导出计算资源分配规则，并与等计算量检查点对比，发现检索指标通常更偏好数据量扩展，但具体推荐依赖于训练目标。预测结果准确且偏保守，对昂贵的大模型训练规划极具价值。本研究为工业级重排序系统提供了实用缩放原则，代码与评估协议将公开。
原文摘要 · Abstract (English)
Scaling laws are well studied for language models and first-stage retrieval, but not for reranking. We present the first systematic study of scaling laws for cross-encoder rerankers across pointwise, pairwise, and listwise objectives. Across model size and training exposure, ranking quality follows predictable power laws, enabling larger rerankers to be forecast from smaller runs. Using models up to 150M parameters, we forecast 400M and 1B rerankers on MSMARCO-dev and TREC DL. Beyond forecasting, we derive compute-allocation rules from the fitted joint scaling law and compare them with equal-compute checkpoints, showing that retrieval metrics often favor data-heavy scaling, though the recommendation depends on the training objective. The forecasts are accurate and typically conservative, making them useful for planning expensive large-model training. These results provide practical scaling principles for industrial reranking systems, and we will release code and evaluation protocols.
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。