mlsanityData to 14 Oct 2026

Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs

arXiv 2505.23304 ↗First posted 29 May 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Generalized Category Discovery (GCD) aims to classify both known and novel categories using partially labeled data that contains only known classes. Despite achieving strong performance on existing benchmarks, current textual GCD methods lack sufficient validation in realistic settings. We introduce Event-Centric GCD (EC-GCD), characterized by long, complex narratives and highly imbalanced class distributions, posing two main challenges: (1) divergent clustering versus classification groupings caused by subjective criteria, and (2) Unfair alignment for minority classes. To tackle these, we propose PaMA, a framework leveraging LLMs to extract and refine event patterns for improved cluster-class alignment. Additionally, a ranking-filtering-mining pipeline ensures balanced representation of prototypes across imbalanced categories. Evaluations on two EC-GCD benchmarks, including a newly constructed Scam Report dataset, demonstrate that PaMA outperforms prior methods with up to 12.58% H-score gains, while maintaining strong generalization on base GCD datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

27 of 39 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2017Deep Bayesian Active Learning with Image Datacited by 819
  6. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  7. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  8. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  9. 2022Generalized Category Discoverycited by 211
  10. 2021Batch Active Learning at Scalecited by 127
  11. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 121
  12. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
15 more
  1. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  2. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 92
  3. 2022A Comparative Survey of Deep Active Learningcited by 89
  4. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  5. 2022Generalized Category Discovery with Decoupled Prototypical Networkcited by 35
  6. 2021On the Importance of Effectively Adapting Pretrained Language Models for Active Learningcited by 32
  7. 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
  8. 2024Happy: A Debiased Learning Framework for Continual Generalized Category Discoverycited by 18
  9. 2020Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Spacecited by 17
  10. 2023Generalized Category Discovery with Large Language Models in the Loopcited by 15
  11. 2023Towards Distribution-Agnostic Generalized Category Discoverycited by 12
  12. 2023DeCrisisMB: Debiased Semi-Supervised Learning for Crisis Tweet Classification via Memory Bankcited by 10
  13. 2022Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discoverycited by 9
  14. 2023Transfer and Alignment Network for Generalized Category Discoverycited by 7
  15. 2025GLEAN: Active Generalized Category Discovery with Diverse LLM Feedbackcited by 6

Built on by

Not cited yet.