mlsanityData to 14 Oct 2026

Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification

arXiv 2412.15603 ↗First posted 20 Dec 2024cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Dialogue intent classification aims to identify the underlying purpose or intent of a user's input in a conversation. Current intent classification systems encounter considerable challenges, primarily due to the vast number of possible intents and the significant semantic overlap among similar intent classes. In this paper, we propose a novel approach to few-shot dialogue intent classification through in-context learning, incorporating dynamic label refinement to address these challenges. Our method retrieves relevant examples for a test input from the training set and leverages a large language model to dynamically refine intent labels based on semantic understanding, ensuring that intents are clearly distinguishable from one another. Experimental results demonstrate that our approach effectively resolves confusion between semantically similar intents, resulting in significantly enhanced performance across multiple datasets compared to baselines. We also show that our method generates more interpretable intent labels, and has a better semantic coherence in capturing underlying user intents compared to baselines.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 19 of its 24 references that are in the map. First posted on arXiv 20 Dec 2024.

Builds on

19 of 24 references.

References · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2024Qwen2 Technical Reportcited by 2,120
  5. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  6. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  7. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  8. 2019BERT for Joint Intent Classification and Slot Fillingcited by 196
  9. 2020DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialoguecited by 89
  10. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
  11. 2023In-Context Learning for Text Classification with Many Labelscited by 35
  12. 2023Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Informationcited by 24
7 more
  1. 2020HINT3: Raising the bar for Intent Detection in the Wildcited by 21
  2. 2023Exploring Zero and Few-shot Techniques for Intent Classificationcited by 21
  3. 2024Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classificationcited by 16
  4. 2023Breaking the Bank with ChatGPT: Few-Shot Text Classification for Financecited by 12
  5. 2023QAID: Question Answering Inspired Few-shot Intent Detectioncited by 5
  6. 2023Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classificationcited by 5
  7. 2023Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Deep Learning Approaches for Multimodal Intent Recognition: A Surveycited by 6
  2. 2025Improving Language Models with Intentional Analysiscited by 2
  3. 2026How DDAIR you? Disambiguated Data Augmentation for Intent Recognitioncited by 1
  4. 2026Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labelingcited by 0
  5. 2026TextClusterLab: An Integrated Framework for Reliable Text Clustering Studiescited by 0
  6. 2026Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Modelscited by 0