mlsanityData to 14 Oct 2026

Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition

arXiv 2310.10184 ↗First posted 16 Oct 2023cs.CL cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

In a practical dialogue system, users may input out-of-domain (OOD) queries. The Generalized Intent Discovery (GID) task aims to discover OOD intents from OOD queries and extend them to the in-domain (IND) classifier. However, GID only considers one stage of OOD learning, and needs to utilize the data in all previous stages for joint training, which limits its wide application in reality. In this paper, we introduce a new task, Continual Generalized Intent Discovery (CGID), which aims to continuously and automatically discover OOD intents from dynamic OOD data streams and then incrementally add them to the classifier with almost no previous data, thus moving towards dynamic intent recognition in an open world. Next, we propose a method called Prototype-guided Learning with Replay and Distillation (PLRD) for CGID, which bootstraps new intent discovery through class prototypes and balances new and old intents through data replay and feature distillation. Finally, we conduct detailed experiments and analysis to verify the effectiveness of PLRD and understand the key challenges of CGID for future research.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

27 of 34 references.

References · 27

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  5. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  6. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  7. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 449
  8. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  9. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  10. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  11. 2019BERT for Joint Intent Classification and Slot Fillingcited by 196
  12. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
15 more
  1. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  2. 2021A Broad Study on the Transferability of Visual Representations with Contrastive Learningcited by 78
  3. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  4. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  5. 2019Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinementcited by 56
  6. 2021Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Taskscited by 46
  7. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  8. 2022Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systemscited by 15
  9. 2022Generalized Intent Discovery: Learning from Open World Dialogue Systemcited by 10
  10. 2022Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discoverycited by 9
  11. 2023A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NERcited by 9
  12. 2021Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classificationcited by 7
  13. 2022Distribution Calibration for Out-of-Domain Detection with Bayesian Approximationcited by 7
  14. 2023A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognitioncited by 6
  15. 2022UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

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

5 papers.

  1. 2024Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detectioncited by 14
  2. 2025RECAP: REwriting Conversations for Intent Understanding in Agentic Planningcited by 7
  3. 2025Decoupling Safety into Orthogonal Subspace: Cost-Efficient and Performance-Preserving Alignment for Large Language Modelscited by 0
  4. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0
  5. 2026Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Spacecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling
  2. 2023Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training
  3. 2024LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification
  4. 2023IntentDial: An Intent Graph based Multi-Turn Dialogue System with Reasoning Path Visualization
  5. 2024Intent Detection in the Age of LLMs
  6. 2021Lifelong Intent Detection via Multi-Strategy Rebalancing
  7. 2026IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference
  8. 2025An Interdisciplinary Review of Commonsense Reasoning and Intent Detection