Saved in:
| Main Authors: | , , |
|---|---|
| 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 |