利用合成数据与基于LLM的监督增强基于Transformer的重排序器
Enhancing Transformer-Based Rerankers with Synthetic Data and LLM-Based Supervision
AI总结：
针对大语言模型重排序计算成本高、小模型微调依赖稀缺人工标注的问题，提出用LLM生成合成查询并标注正负对、以LCE损失对比学习微调小Transformer重排序器的方法，在MedQuAD上提升了域内性能与域外泛化性，降低了成本。
摘要：
高效的文档重排序对于提升各类应用的搜索相关性至关重要。大语言模型（LLMs）凭借深度语义理解与推理能力在重排序任务中表现出色，但其高昂的计算成本使其难以应用于多数实际部署场景。微调规模更小的任务专用模型是更高效的替代方案，但这类方法通常依赖稀缺的人工标注数据。为解决这一问题，我们提出了一种无需人工标注查询-文档对的新型流水线。我们的方法利用LLMs从特定领域语料库生成合成查询，并采用基于LLM的分类器标注正例对与难负例对。随后，我们使用该合成数据集，借助局部对比估计（LCE）损失，以对比学习方式微调一个规模更小的transformer模型。在MedQuAD数据集上的实验表明，我们的方法显著提升了域内性能，且在域外任务上也具备良好的泛化能力。通过将LLMs用于数据生成与监督而非推理，我们在保持强大重排序能力的同时降低了计算成本。
英文摘要：
Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational cost makes them impractical for many real-world deployments. Fine-tuning smaller, task-specific models is a more efficient alternative but typically depends on scarce, manually labeled data. To overcome this, we propose a novel pipeline that eliminates the need for human-labeled query-document pairs. Our method uses LLMs to generate synthetic queries from domain-specific corpora and employs an LLM-based classifier to label positive and hard-negative pairs. This synthetic dataset is then used to fine-tune a smaller transformer model with contrastive learning using Localized Contrastive Estimation (LCE) loss. Experiments on the MedQuAD dataset show that our approach significantly boosts in-domain performance and generalizes well to out-of-domain tasks. By using LLMs for data generation and supervision rather than inference, we reduce computational costs while maintaining strong reranking capabilities.
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。
