Saved in:
Bibliographic Details
Main Authors: Luo, Yi, Wang, Qiwen, Yang, Junqi, Tang, Luyao, Lin, Zhenghao, Ying, Zhenzhe, Wang, Weiqiang, Lin, Chen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.23304
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916766250172416
author Luo, Yi
Wang, Qiwen
Yang, Junqi
Tang, Luyao
Lin, Zhenghao
Ying, Zhenzhe
Wang, Weiqiang
Lin, Chen
author_facet Luo, Yi
Wang, Qiwen
Yang, Junqi
Tang, Luyao
Lin, Zhenghao
Ying, Zhenzhe
Wang, Weiqiang
Lin, Chen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23304
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs
Luo, Yi
Wang, Qiwen
Yang, Junqi
Tang, Luyao
Lin, Zhenghao
Ying, Zhenzhe
Wang, Weiqiang
Lin, Chen
Computation and Language
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.
title Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs
topic Computation and Language
url https://arxiv.org/abs/2505.23304