Study on LLMs for Promptagator-Style Dense Retriever Training
Not on the map. Why?
Abstract (arXiv)
Promptagator demonstrated that Large Language Models (LLMs) with few-shot prompts can be used as task-specific query generators for fine-tuning domain-specialized dense retrieval models. However, the original Promptagator approach relied on proprietary and large-scale LLMs which users may not have access to or may be prohibited from using with sensitive data. In this work, we study the impact of open-source LLMs at accessible scales (≤14B parameters) as an alternative. Our results demonstrate that open-source LLMs as small as 3B parameters can serve as effective Promptagator-style query generators. We hope our work will inform practitioners with reliable alternatives for synthetic data generation and give insights to maximize fine-tuning results for domain-specific applications.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 2 Oct 2025.
Builds on
19 of 26 references.
References · 19
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
- 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
- 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
- 2023LIMA: Less Is More for Alignmentcited by 1,080
- 2019Passage Re-ranking with BERTcited by 629
- 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
7 more
- 2023Large language models can accurately predict searcher preferencescited by 129
- 2021Scaling Deep Contrastive Learning Batch Size under Memory Limited Setupcited by 123
- 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
- 2023InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrievalcited by 73
- 2024LLM-based relevance assessment still can't replace human relevance assessmentcited by 27
- 2023InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankerscited by 14
- 2025LLMs can be Fooled into Labelling a Document as Relevant (best caf'e near me; this paper is perfectly relevant)cited by 10
Built on by
Citing papers per year: 2026: 2.
2 papers.