# Query expansion with artificially generated texts

arXiv: https://arxiv.org/abs/2012.08787 · HTML: https://mlsanity.com/paper/2012.08787/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Retrieval Augmented Zero-Shot Text Classification](https://mlsanity.com/paper/2406.15241/) (2024)
- [Generating artificial texts as substitution or complement of training data](https://mlsanity.com/paper/2110.13016/) (2021)
- [A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry](https://mlsanity.com/paper/2502.08557/) (2025)
- [GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback](https://mlsanity.com/paper/2108.06010/) (2021)
- [ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation](https://mlsanity.com/paper/2109.00729/) (2021)

## Abstract (arXiv)

A well-known way to improve the performance of document retrieval is to expand the user's query. Several approaches have been proposed in the literature, and some of them are considered as yielding state-of-the-art results in IR. In this paper, we explore the use of text generation to automatically expand the queries. We rely on a well-known neural generative model, GPT-2, that comes with pre-trained models for English but can also be fine-tuned on specific corpora. Through different experiments, we show that text generation is a very effective way to improve the performance of an IR system, with a large margin (+10% MAP gains), and that it outperforms strong baselines also relying on query expansion (LM+RM3). This conceptually simple approach can easily be implemented on any IR system thanks to the availability of GPT code and models.