mlsanityData to 14 Oct 2026

Exploring Zero and Few-shot Techniques for Intent Classification

arXiv 2305.07157 ↗First posted 11 May 2023cs.CL cs.AIcited by 21

Not on the map. Why?

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

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

15 of 20 references.

References · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  6. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  7. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  8. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  9. 2019Multilingual Universal Sentence Encoder for Semantic Retrievalcited by 193
  10. 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 146
  11. 2022Data Augmentation for Intent Classification with Off-the-shelf Large Language Modelscited by 49
  12. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
3 more
  1. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  2. 2019An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classificationcited by 20
  3. 2022Data Augmentation for Intent Classificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 10; 2025: 7; 2026: 1.

21 papers.

Sort:

By area:

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2023User Modeling in the Era of Large Language Models: Current Research and Future Directionscited by 18
  3. 2023End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directionscited by 17
  4. 2025VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcarecited by 17
  5. 2025Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Samplingcited by 12
  6. 2024Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisionscited by 11
  7. 2024A Survey of Ontology Expansion for Conversational Understandingcited by 6
  8. 2024Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classificationcited by 6
  9. 2025GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasetscited by 6
  10. 2023Prompted Zero-Shot Multi-label Classification of Factual Incorrectness in Machine-Generated Summariescited by 5
  11. 2024ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Fillercited by 5
  12. 2024Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generationcited by 4
9 more
  1. 2025PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowchartscited by 3
  2. 2024Domain Adaptable Prescriptive AI Agent for Enterprisecited by 2
  3. 2024Practical token pruning for foundation models in few-shot conversational virtual assistant systemscited by 1
  4. 2025Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routingcited by 1
  5. 2025Few-Shot Query Intent Detection via Relation-Aware Prompt Learningcited by 1
  6. 2024Intent Classification for Bank Chatbots through LLM Fine-Tuningcited by 0
  7. 2024CALICO: Conversational Agent Localization via Synthetic Data Generationcited by 0
  8. 2025Unveiling Dual Quality in Product Reviews: An NLP-Based Approachcited by 0
  9. 2026Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuningcited by 0