用测试时自适应提升对话查询重写效果，不依赖训练数据
AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation
- 通过奖励模型在推理时动态选择最优重写结果
- 在5个数据集上均显著优于现有方法
- 可适配黑盒大模型接口，实用性强
基于提示的对话查询重写已成为对话搜索中的有效方法，能将模糊用户查询转化为独立搜索词。基于提示生成候选并采用Best-of-N策略展现强大扩展潜力。然而，以往的调优方法（训练时）与适应方法（测试时）均未能充分释放其优势。本文提出AdaRewriter，一种基于输出监督奖励模型的测试时自适应框架，用于查询重写。通过对比排序损失训练轻量级奖励模型，在推理阶段选择最优重写结果。该方法可在黑盒系统中运行，包括商业大模型API。在五个对话搜索数据集上的实验表明，AdaRewriter在多数设置下显著优于现有方法，验证了测试时自适应在对话查询重写中的潜力。
原文摘要 · Abstract (English)
Prompting-based conversational query reformulation has emerged as a powerful approach for conversational search, refining ambiguous user queries into standalone search queries. Best-of-N reformulation over the generated candidates via prompting shows impressive potential scaling capability. However, both the previous tuning methods (training time) and adaptation approaches (test time) can not fully unleash their benefits. In this paper, we propose AdaRewriter, a novel framework for query reformulation using an outcome-supervised reward model via test-time adaptation. By training a lightweight reward model with contrastive ranking loss, AdaRewriter selects the most promising reformulation during inference. Notably, it can operate effectively in black-box systems, including commercial LLM APIs. Experiments on five conversational search datasets show that AdaRewriter significantly outperforms the existing methods across most settings, demonstrating the potential of test-time adaptation for conversational query reformulation.
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。