# Exploring Zero and Few-shot Techniques for Intent Classification

arXiv: https://arxiv.org/abs/2305.07157 · HTML: https://mlsanity.com/paper/2305.07157/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 11 May 2023.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Multilingual Universal Sentence Encoder for Semantic Retrieval](https://mlsanity.com/paper/1907.04307/) (2019)
- [MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages](https://mlsanity.com/paper/2204.08582/) (2022)
- [Data Augmentation for Intent Classification with Off-the-shelf Large Language Models](https://mlsanity.com/paper/2204.01959/) (2022)
- [Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning](https://mlsanity.com/paper/2109.06349/) (2021)
- [Few-shot Intent Classification and Slot Filling with Retrieved Examples](https://mlsanity.com/paper/2104.05763/) (2021)
- [An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification](https://mlsanity.com/paper/1912.09297/) (2019)
- [Data Augmentation for Intent Classification](https://mlsanity.com/paper/2206.05790/) (2022)

## Built on by (most cited first, 21 of 21)

- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [User Modeling in the Era of Large Language Models: Current Research and Future Directions](https://mlsanity.com/paper/2312.11518/) (2023)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare](https://mlsanity.com/paper/2502.13775/) (2025)
- [Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling](https://mlsanity.com/paper/2504.13592/) (2025)
- [Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions](https://mlsanity.com/paper/2410.02028/) (2024)
- [A Survey of Ontology Expansion for Conversational Understanding](https://mlsanity.com/paper/2410.15019/) (2024)
- [Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification](https://mlsanity.com/paper/2412.15603/) (2024)
- [GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets](https://mlsanity.com/paper/2504.19898/) (2025)
- [Prompted Zero-Shot Multi-label Classification of Factual Incorrectness in Machine-Generated Summaries](https://mlsanity.com/paper/2312.01087/) (2023)
- [ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler](https://mlsanity.com/paper/2403.17536/) (2024)
- [Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generation](https://mlsanity.com/paper/2404.00361/) (2024)
- [PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts](https://mlsanity.com/paper/2503.06706/) (2025)
- [Domain Adaptable Prescriptive AI Agent for Enterprise](https://mlsanity.com/paper/2407.20447/) (2024)
- [Practical token pruning for foundation models in few-shot conversational virtual assistant systems](https://mlsanity.com/paper/2408.11799/) (2024)
- [Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing](https://mlsanity.com/paper/2507.01541/) (2025)
- [Few-Shot Query Intent Detection via Relation-Aware Prompt Learning](https://mlsanity.com/paper/2509.05635/) (2025)
- [Intent Classification for Bank Chatbots through LLM Fine-Tuning](https://mlsanity.com/paper/2410.04925/) (2024)
- [CALICO: Conversational Agent Localization via Synthetic Data Generation](https://mlsanity.com/paper/2412.05388/) (2024)
- [Unveiling Dual Quality in Product Reviews: An NLP-Based Approach](https://mlsanity.com/paper/2505.19254/) (2025)
- [Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning](https://mlsanity.com/paper/2603.27057/) (2026)

## Abstract (arXiv)

Conversational NLU providers often need to scale to thousands of intent-classification models where new customers often face the cold-start problem. Scaling to so many customers puts a constraint on storage space as well. In this paper, we explore four different zero and few-shot intent classification approaches with this low-resource constraint: 1) domain adaptation, 2) data augmentation, 3) zero-shot intent classification using descriptions large language models (LLMs), and 4) parameter-efficient fine-tuning of instruction-finetuned language models. Our results show that all these approaches are effective to different degrees in low-resource settings. Parameter-efficient fine-tuning using T-few recipe (Liu et al., 2022) on Flan-T5 (Chang et al., 2022) yields the best performance even with just one sample per intent. We also show that the zero-shot method of prompting LLMs using intent descriptions