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

arXiv:2402.11827v1 Announce Type: cross
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 …

abstract arxiv context conversational conversational search cs.cl cs.ir current dialogue language language models large language large language models query question questions retrieval search tasks type understanding