CONVERSER: Few-shot Conversational Dense Retrieval With Synthetic Data Generation

Abstract

Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversational IR. However, training dense retrievers requires large amounts of in-domain paired data. This hinders the development of conversational dense retrievers, as abundant in-domain conversations are expensive to collect. In this paper, we propose CONVERSER, a framework for training conversational dense retrievers with at most 6 examples of in-domain dialogues. Specifically, we utilize the in-context learning capability of large language models to generate conversational queries given a passage in the retrieval corpus. Experimental results on conversational retrieval benchmarks OR-QuAC and TREC CAsT 19 show that the proposed CONVERSER achieves comparable performance to fully-supervised models, demonstrating the effectiveness of our proposed framework in few-shot conversational dense retrieval. All source code and

Stats

• citations6
• S2 citations—
• github stars8
• HF likes0
• heat score8.25
• arxiv keyhuang2023converser

Related papers

• Few-shot Conversational Dense Retrieval (2021)16.68
• Dense Passage Retrieval In Conversational Search (2025)0.00
• Contextualized Query Embeddings For Conversational Search (2021)10.21
• Interpreting Conversational Dense Retrieval By Rewriting-enhanced Inversion Of Session Embedding (2024)6.77
• Domain Adaptation For Dense Retrieval And Conversational Dense Retrieval Through Self-supervision By Meticulous Pseudo-relevance Labeling (2024)0.00
• Chatsearch: A Dataset And A Generative Retrieval Model For General Conversational Image Retrieval (2024)2.00
• Uniretriever: Multi-task Candidates Selection For Various Context-adaptive Conversational Retrieval (2024)0.00
• Cosplade: Contextualizing SPLADE For Conversational Information Retrieval (2023)6.77