# CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation

arXiv: https://arxiv.org/abs/2309.06748 · HTML: https://mlsanity.com/paper/2309.06748/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 13 Sep 2023.

## Placed in

- Synthetic data and self-improvement for LLMs / [LLM synthetic data generation](https://mlsanity.com/synth/llm-synthetic-data-generation/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [Synthetic QA Corpora Generation with Roundtrip Consistency](https://mlsanity.com/paper/1906.05416/) (2019)
- [Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup](https://mlsanity.com/paper/2101.06983/) (2021)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [TopiOCQA: Open-domain Conversational Question Answering with Topic Switching](https://mlsanity.com/paper/2110.00768/) (2021)
- [Few-Shot Conversational Dense Retrieval](https://mlsanity.com/paper/2105.04166/) (2021)
- [CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning](https://mlsanity.com/paper/2112.08558/) (2021)
- [Dialog Inpainting: Turning Documents into Dialogs](https://mlsanity.com/paper/2205.09073/) (2022)
- [FlowQA: Grasping Flow in History for Conversational Machine Comprehension](https://mlsanity.com/paper/1810.06683/) (2018)
- [FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension](https://mlsanity.com/paper/1908.05117/) (2019)
- [Generating Information-Seeking Conversations from Unlabeled Documents](https://mlsanity.com/paper/2205.12609/) (2022)
- [Open-Domain Conversational Question Answering with Historical Answers](https://mlsanity.com/paper/2211.09401/) (2022)
- [A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering](https://mlsanity.com/paper/2104.08443/) (2021)
- [An Empirical Study of Content Understanding in Conversational Question Answering](https://mlsanity.com/paper/1909.10743/) (2019)
- [Multifaceted Improvements for Conversational Open-Domain Question Answering](https://mlsanity.com/paper/2204.00266/) (2022)

## Built on by (most cited first, 6 of 6)

- [A Survey on Recent Advances in Conversational Data Generation](https://mlsanity.com/paper/2405.13003/) (2024)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [Self-Retrieval: End-to-End Information Retrieval with One Large Language Model](https://mlsanity.com/paper/2403.00801/) (2024)
- [Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling](https://mlsanity.com/paper/2403.03516/) (2024)
- [LLM-Oriented Information Retrieval: A Denoising-First Perspective](https://mlsanity.com/paper/2605.00505/) (2026)
- [ASMR: Augmenting Life Scenario using Large Generative Models for Robotic Action Reflection](https://mlsanity.com/paper/2506.13956/) (2025)

## Abstract (arXiv)

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 generated datasets are available at https://github.com/MiuLab/CONVERSER