# InPars: Data Augmentation for Information Retrieval using Large Language Models

arXiv: https://arxiv.org/abs/2202.05144 · HTML: https://mlsanity.com/paper/2202.05144/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 54 references that are in the map.
- First posted on arXiv 10 Feb 2022.

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://mlsanity.com/paper/1805.06201/) (2018)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Not Enough Data? Deep Learning to the Rescue!](https://mlsanity.com/paper/1911.03118/) (2019)
- [Data Augmentation using Pre-trained Transformer Models](https://mlsanity.com/paper/2003.02245/) (2020)
- [Data Augmentation for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1705.00440/) (2017)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [Deeper Text Understanding for IR with Contextual Neural Language Modeling](https://mlsanity.com/paper/1905.09217/) (2019)
- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models](https://mlsanity.com/paper/2101.05667/) (2021)
- [AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization](https://mlsanity.com/paper/2103.11332/) (2021)
- [Generative Data Augmentation for Commonsense Reasoning](https://mlsanity.com/paper/2004.11546/) (2020)

## Built on by (most cited first, 30 of 62)

- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [Gecko: Versatile Text Embeddings Distilled from Large Language Models](https://mlsanity.com/paper/2403.20327/) (2024)
- [InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval](https://mlsanity.com/paper/2301.01820/) (2023)
- [AI-Generated Content (AIGC): A Survey](https://mlsanity.com/paper/2304.06632/) (2023)
- [Language Models in the Loop: Incorporating Prompting into Weak Supervision](https://mlsanity.com/paper/2205.02318/) (2022)
- [Questions Are All You Need to Train a Dense Passage Retriever](https://mlsanity.com/paper/2206.10658/) (2022)
- [Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models](https://mlsanity.com/paper/2409.11136/) (2024)
- [UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers](https://mlsanity.com/paper/2303.00807/) (2023)
- [DSI++: Updating Transformer Memory with New Documents](https://mlsanity.com/paper/2212.09744/) (2022)
- [A Survey on Data Augmentation in Large Model Era](https://mlsanity.com/paper/2401.15422/) (2024)
- [Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.18676/) (2024)
- [RaDeR: Reasoning-aware Dense Retrieval Models](https://mlsanity.com/paper/2505.18405/) (2025)
- [Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction](https://mlsanity.com/paper/2307.01128/) (2023)
- [I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench](https://mlsanity.com/paper/2401.17882/) (2024)
- [DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers](https://mlsanity.com/paper/2502.18460/) (2025)
- [Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matchers](https://mlsanity.com/paper/2307.03539/) (2023)
- [Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation](https://mlsanity.com/paper/2503.19092/) (2025)
- [UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?](https://mlsanity.com/paper/2306.16931/) (2023)
- [Context Aware Query Rewriting for Text Rankers using LLM](https://mlsanity.com/paper/2308.16753/) (2023)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [IncDSI: Incrementally Updatable Document Retrieval](https://mlsanity.com/paper/2307.10323/) (2023)
- [GLaD: Geometric Latent Distillation for Vision-Language-Action Models](https://mlsanity.com/paper/2512.09619/) (2025)
- [Exploring the Viability of Synthetic Query Generation for Relevance Prediction](https://mlsanity.com/paper/2305.11944/) (2023)
- [Dense Retrieval Adaptation using Target Domain Description](https://mlsanity.com/paper/2307.02740/) (2023)
- [cTBLS: Augmenting Large Language Models with Conversational Tables](https://mlsanity.com/paper/2303.12024/) (2023)
- [Selecting which Dense Retriever to use for Zero-Shot Search](https://mlsanity.com/paper/2309.09403/) (2023)
- [Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking](https://mlsanity.com/paper/2404.08535/) (2024)

## Abstract (arXiv)

The information retrieval community has recently witnessed a revolution due to large pretrained transformer models. Another key ingredient for this revolution was the MS MARCO dataset, whose scale and diversity has enabled zero-shot transfer learning to various tasks. However, not all IR tasks and domains can benefit from one single dataset equally. Extensive research in various NLP tasks has shown that using domain-specific training data, as opposed to a general-purpose one, improves the performance of neural models. In this work, we harness the few-shot capabilities of large pretrained language models as synthetic data generators for IR tasks. We show that models finetuned solely on our unsupervised dataset outperform strong baselines such as BM25 as well as recently proposed self-supervised dense retrieval methods. Furthermore, retrievers finetuned on both supervised and our synthetic data achieve better zero-shot transfer than models finetuned only on supervised data. Code, models, and data are available at https://github.com/zetaalphavector/inpars .