Javier Parapar — accepted AI-conference papers

2025

Decoding Hate: Exploring Language Models’ Reactions to Hate Speech

NAACL 2025long

Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate hate speech patterns, given their training on vast amounts o…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2025

Enhancing Discourse Parsing for Local Structures from Social Media with LLM-Generated Data

Martial Pastor, Nelleke Oostdijk, Patricia Martin-Rodilla, Javier Parapar

COLING 2025main

We explore the use of discourse parsers for extracting a particular discourse structure in a real-world social media scenario. Specifically, we focus on enhancing parser performance through the integration of synthetic data generated by large language models (LLMs). We conduct experiments using a ne…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗