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

TL;DR

This paper introduces PaMA, a novel framework leveraging large language models to improve generalized category discovery in complex, event-centric narratives with imbalanced classes, demonstrating significant performance gains.

Contribution

The paper presents PaMA, a new LLM-based method for event-centric GCD that addresses subjective clustering and class imbalance, validated on new and existing benchmarks.

Findings

PaMA outperforms prior methods with up to 12.58% H-score improvements.

It maintains strong generalization on standard GCD datasets.

Effective handling of complex narratives and class imbalance.

Abstract

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.