Event Detection with a Context-Aware Encoder and LoRA for Improved Performance on Long-Tailed Classes

TL;DR

This paper improves event detection by using a context-aware encoder and LoRA finetuning, addressing limitations of unidirectional models and better evaluating performance on long-tail classes with Macro-F1 scores.

Contribution

It introduces a context-aware encoder and demonstrates that LoRA finetuning significantly enhances performance on long-tailed event classes in event detection tasks.

Findings

Models with sentence context outperform baseline models.

LoRA finetuning boosts Macro-F1 scores, especially for long-tail classes.

Macro-F1 is a more balanced metric than Micro-F1 for event detection.

Abstract

The current state of event detection research has two notable re-occurring limitations that we investigate in this study. First, the unidirectional nature of decoder-only LLMs presents a fundamental architectural bottleneck for natural language understanding tasks that depend on rich, bidirectional context. Second, we confront the conventional reliance on Micro-F1 scores in event detection literature, which systematically inflates performance by favoring majority classes. Instead, we focus on Macro-F1 as a more representative measure of a model's ability across the long-tail of event types. Our experiments demonstrate that models enhanced with sentence context achieve superior performance over canonical decoder-only baselines. Using Low-Rank Adaptation (LoRA) during finetuning provides a substantial boost in Macro-F1 scores in particular, especially for the decoder-only models, showing that LoRA can be an effective tool to enhance LLMs' performance on long-tailed event classes.