@inproceedings{yoon-etal-2025-ask,
    title = "Ask Optimal Questions: Aligning Large Language Models with Retriever{'}s Preference in Conversation",
    author = "Yoon, Chanwoong  and
      Kim, Gangwoo  and
      Jeon, Byeongguk  and
      Kim, Sungdong  and
      Jo, Yohan  and
      Kang, Jaewoo",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.328/",
    pages = "5899--5921",
    ISBN = "979-8-89176-195-7",
    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 demonstrates superiority on two benchmarks, surpassing the previous state-of-the-art performance of rewrite-then-retrieve approaches, including GPT-3.5."
}