提出最优问题：在对话中让大语言模型与检索器偏好对齐
Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation
AI总结：
针对对话式搜索中现有重写-检索方法查询重写效果不佳的问题，提出RetPO框架，通过构建含41万+重写反馈的RF collection数据集微调小模型，实现与检索器偏好对齐，性能超现有SOTA。
摘要：
与单轮检索任务不同，对话式搜索需要在对话语境中理解当前问题。常见的“重写-检索”方法旨在将问题去语境化，使其具备自足性以适配现成检索器，但现有方法大多因整合检索结果信号的能力有限，生成的查询重写结果并非最优。为解决这一局限，我们提出全新框架RetPO（检索器偏好优化），该框架用于优化语言模型（LM），使其生成的搜索查询重写结果符合目标检索系统的偏好。该流程首先通过提示大语言模型生成多种潜在重写结果，随后收集这些重写结果的检索性能作为检索器的偏好。通过这一过程，我们构建了名为RF collection的大规模数据集，包含1.2万组对话中超过41万条查询重写的检索器反馈。此外，我们在该数据集上微调了一个更小的语言模型，使其与检索器反馈对齐。我们的最终模型在两个基准测试上表现优异，超越了此前“重写-检索”方法的最优性能。
英文摘要：
Conversational search, unlike single-turn retrieval tasks, requires understanding the current question within a dialogue context. The common approach of rewrite-then-retrieve aims to decontextualize questions to be self-sufficient for off-the-shelf retrievers, but most existing methods produce sub-optimal query rewrites due to the limited ability to incorporate signals from the retrieval results. To overcome this limitation, we present a novel framework RetPO (Retriever's Preference Optimization), which is designed to optimize a language model (LM) for reformulating search queries in line with the preferences of the target retrieval systems. The process begins by prompting a large LM to produce various potential rewrites and then collects retrieval performance for these rewrites as the retrievers' preferences. Through the process, we construct a large-scale dataset called RF collection, containing Retrievers' Feedback on over 410K query rewrites across 12K conversations. Furthermore, we fine-tune a smaller LM on this dataset to align it with the retrievers' feedback. Our resulting model demonstrates superiority on two benchmarks, surpassing the previous state-of-the-art performance of rewrite-then-retrieve approaches.
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。
