Saved in:
Bibliographic Details
Main Authors: Monsur, Abdullah Al, Bommisetty, Nitesh Vamshi, Kim, Gene Louis
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.11932
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914333697507328
author Monsur, Abdullah Al
Bommisetty, Nitesh Vamshi
Kim, Gene Louis
author_facet Monsur, Abdullah Al
Bommisetty, Nitesh Vamshi
Kim, Gene Louis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11932
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Event Detection with a Context-Aware Encoder and LoRA for Improved Performance on Long-Tailed Classes
Monsur, Abdullah Al
Bommisetty, Nitesh Vamshi
Kim, Gene Louis
Computation and Language
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.
title Event Detection with a Context-Aware Encoder and LoRA for Improved Performance on Long-Tailed Classes
topic Computation and Language
url https://arxiv.org/abs/2601.11932