# Synthetic Query Generation using Large Language Models for Virtual Assistants

arXiv: https://arxiv.org/abs/2406.06729 · HTML: https://mlsanity.com/paper/2406.06729/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 10 Jun 2024.

## Builds on (most cited first, 8 of 8)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?](https://mlsanity.com/paper/2302.03495/) (2023)
- [Scalable language model adaptation for spoken dialogue systems](https://mlsanity.com/paper/1812.04647/) (2018)
- [Connecting and Comparing Language Model Interpolation Techniques](https://mlsanity.com/paper/1908.09738/) (2019)
- [Predicting Entity Popularity to Improve Spoken Entity Recognition by Virtual Assistants](https://mlsanity.com/paper/2005.12816/) (2020)
- [Error-driven Pruning of Language Models for Virtual Assistants](https://mlsanity.com/paper/2102.07219/) (2021)
- [A Discriminative Entity-Aware Language Model for Virtual Assistants](https://mlsanity.com/paper/2106.11292/) (2021)
- [The Birth of Collective Memories: Analyzing Emerging Entities in Text Streams](https://mlsanity.com/paper/1701.04039/) (2017)

## Built on by (most cited first, 9 of 9)

- [Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning](https://mlsanity.com/paper/2501.01124/) (2025)
- [Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation](https://mlsanity.com/paper/2502.11181/) (2025)
- [Transformer-based Model for ASR N-Best Rescoring and Rewriting](https://mlsanity.com/paper/2406.08207/) (2024)
- [Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation](https://mlsanity.com/paper/2505.16065/) (2025)
- [Towards Evaluating Large Language Models for Graph Query Generation](https://mlsanity.com/paper/2411.08449/) (2024)
- [Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction](https://mlsanity.com/paper/2506.06117/) (2025)
- [Instituto de Telecomunicacc~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning](https://mlsanity.com/paper/2506.17019/) (2025)
- [Image-Seeking Intent Prediction for Cross-Device Product Search](https://mlsanity.com/paper/2511.14764/) (2025)
- [Improving Scientific Document Retrieval with Academic Concept Index](https://mlsanity.com/paper/2601.00567/) (2026)

## Abstract (arXiv)

Virtual Assistants (VAs) are important Information Retrieval platforms that help users accomplish various tasks through spoken commands. The speech recognition system (speech-to-text) uses query priors, trained solely on text, to distinguish between phonetically confusing alternatives. Hence, the generation of synthetic queries that are similar to existing VA usage can greatly improve upon the VA's abilities -- especially for use-cases that do not (yet) occur in paired audio/text data. In this paper, we provide a preliminary exploration of the use of Large Language Models (LLMs) to generate synthetic queries that are complementary to template-based methods. We investigate whether the methods (a) generate queries that are similar to randomly sampled, representative, and anonymized user queries from a popular VA, and (b) whether the generated queries are specific. We find that LLMs generate more verbose queries, compared to template-based methods, and reference aspects specific to the entity. The generated queries are similar to VA user queries, and are specific enough to retrieve the relevant entity. We conclude that queries generated by LLMs and templates are complementary.