← Search

Chiara Di Bonaventura

2 accepted papers

2025

From Detection to Explanation: Effective Learning Strategies for LLMs in Online Abusive Language Research

COLING 2025main

Abusive language detection relies on understanding different levels of intensity, expressiveness and targeted groups, which requires commonsense reasoning, world knowledge and linguistic nuances that evolve over time. Here, we frame the problem as a knowledge-guided learning task, and demonstrate th…

2025

Hatevolution: What Static Benchmarks Don’t Tell Us

ACL 2025finding

Language changes over time, including in the hate speech domain, which evolves quickly following social dynamics and cultural shifts. While NLP research has investigated the impact of language evolution on model training and has proposed several solutions for it, its impact on model benchmarking rem…