ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval

arXiv:2404.13556v1 Announce Type: cross
Abstract: Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent complex conversational sessions for dense retrieval. To achieve this, we propose a simple and effective dual-learning approach that adapts LLM for retrieval via contrastive learning while enhancing the complex session understanding through masked instruction tuning on high-quality conversational instruction tuning data. Extensive experiments on five conversational …

abstract arxiv capability conversational conversational search cs.cl cs.ir generalized interpretation language language models large language large language models paper retrieval robust search simple type