Ask Optimal Questions: Aligning Large Language Models with Retriever’s Preference in Conversational Search

Anonymous

Abstract: 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 using this dataset to align it with the retrievers' preferences as feedback.The resulting model achieves state-of-the-art performance on two recent conversational search benchmarks, significantly outperforming existing baselines, including GPT-3.5.

Paper Type: long

Research Area: Information Retrieval and Text Mining

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English