# Generate then Refine: Data Augmentation for Zero-shot Intent Detection

arXiv: https://arxiv.org/abs/2410.01953 · HTML: https://mlsanity.com/paper/2410.01953/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 2 Oct 2024.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Neural Data Augmentation via Example Extrapolation](https://mlsanity.com/paper/2102.01335/) (2021)
- [Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference](https://mlsanity.com/paper/2010.13009/) (2020)
- [Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information](https://mlsanity.com/paper/2302.05096/) (2023)
- [Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search](https://mlsanity.com/paper/2405.03480/) (2024)
- [CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection](https://mlsanity.com/paper/2004.01881/) (2020)
- [A Survey on Recent Advances in Conversational Data Generation](https://mlsanity.com/paper/2405.13003/) (2024)
- [Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-shot In-Context Learners](https://mlsanity.com/paper/2212.10873/) (2022)
- [ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection](https://mlsanity.com/paper/2308.13517/) (2023)
- [Another Diversity-Promoting Objective Function for Neural Dialogue Generation](https://mlsanity.com/paper/1811.08100/) (2018)
- [Quick Starting Dialog Systems with Paraphrase Generation](https://mlsanity.com/paper/2204.02546/) (2022)
- [MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classification](https://mlsanity.com/paper/2204.04952/) (2022)

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

- [SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models](https://mlsanity.com/paper/2503.15351/) (2025)
- [Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations](https://mlsanity.com/paper/2507.22289/) (2025)
- [How DDAIR you? Disambiguated Data Augmentation for Intent Recognition](https://mlsanity.com/paper/2601.11234/) (2026)
- [PromptAug: Fine-grained Conflict Classification Using Data Augmentation](https://mlsanity.com/paper/2506.22491/) (2025)
- [Cognitive Alignment in Personality Reasoning: Leveraging Prototype Theory for MBTI Inference](https://mlsanity.com/paper/2511.00115/) (2025)
- [The Significance of Style Diversity in Annotation-Free Synthetic Data Generation](https://mlsanity.com/paper/2606.20400/) (2026)

## Abstract (arXiv)

In this short paper we propose a data augmentation method for intent detection in zero-resource domains. Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive in settings with many possible intents. We use a two-stage approach: First, we generate utterances for intent labels using an open-source large language model in a zero-shot setting. Second, we develop a smaller sequence-to-sequence model (the Refiner), to improve the generated utterances. The Refiner is fine-tuned on seen domains and then applied to unseen domains. We evaluate our method by training an intent classifier on the generated data, and evaluating it on real (human) data. We find that the Refiner significantly improves the data utility and diversity over the zero-shot LLM baseline for unseen domains and over common baseline approaches. Our results indicate that a two-step approach of a generative LLM in zero-shot setting and a smaller sequence-to-sequence model can provide high-quality data for intent detection.