Papers by Julien Longhi
[MASK]ED - Language Modeling for Explainable Classification and Disentangling of Socially Unacceptable Discourse. (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained PMLMs often degrade in multi-label SUD classification due to overlapping linguistic cues. |
| Approach: | They propose an artifact-guided pre-training strategy that injects statistically salient linguistic features into masked language models to enhance generalization across discourse types. |
| Outcome: | The proposed approach improves performance in 10 datasets extensively used in SUD classification benchmarks. |