mlsanityData to 7 Oct 2026

Conformal Intent Classification and Clarification for Fast and Accurate Intent Recognition

arXiv 2403.18973 ↗First posted 27 Mar 2024cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

We present Conformal Intent Classification and Clarification (CICC), a framework for fast and accurate intent classification for task-oriented dialogue systems. The framework turns heuristic uncertainty scores of any intent classifier into a clarification question that is guaranteed to contain the true intent at a pre-defined confidence level. By disambiguating between a small number of likely intents, the user query can be resolved quickly and accurately. Additionally, we propose to augment the framework for out-of-scope detection. In a comparative evaluation using seven intent recognition datasets we find that CICC generates small clarification questions and is capable of out-of-scope detection. CICC can help practitioners and researchers substantially in improving the user experience of dialogue agents with specific clarification questions.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

18 of 43 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  3. 2020Classification with Valid and Adaptive Coveragecited by 390
  4. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  5. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 365
  6. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  7. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 270
  8. 2019Benchmarking Natural Language Understanding Services for building Conversational Agentscited by 166
  9. 2018Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialogcited by 124
  10. 2017DOC: Deep Open Classification of Text Documentscited by 109
  11. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 70
  12. 2019Deep Unknown Intent Detection with Margin Losscited by 66
6 more
  1. 2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
  2. 2021Conformal Bayesian Computationcited by 38
  3. 2022Conformal Prediction Sets with Limited False Positivescited by 28
  4. 2020Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questionscited by 16
  5. 2021Diverse and Specific Clarification Question Generation with Keywordscited by 10
  6. 2019Reinforcement Learning for Personalized Dialogue Managementcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialoguescited by 11
  2. 2025Hierarchical Conformal Classificationcited by 2
  3. 2025Detecting Linguistic Bias in Government Documents Using Large language Modelscited by 1
  4. 2026The Significance of Style Diversity in Annotation-Free Synthetic Data Generationcited by 0