F. Batista

Assessing LLMs for Culturally Sensitive Communication in European Portuguese

Cost-Effective Hate Speech Detection in Portuguese Using Lightweight LLMs

This work evaluates the efficiency and competitiveness of seven smaller, more accessible LLMs through zero-shot classification with structured instructions, leveraging the expert-annotated test dataset and annotation scheme of the kNOwHATE project to demonstrate a viable, competitive, and low-cost approach that does no...

Polarizations in Static Word Embeddings: Investigating Bias in Marginalized Dialects of Portuguese

It is suggested that static word embeddings applied to Pajubá fail to capture the sociolinguistic complexity of Pajubá and systematically reflect the dominant and often discriminatory discourses present in the training corpora.

Gender Bias Evaluation in English-Portuguese Automated Translation Outputs

This work contributes a preliminary cross-system comparison for an underexplored language pair and lays the groundwork for larger-scale evaluations of gender-inclusive AT, indicating that all four models struggle to faithfully convey gender information from source to target.

Optimising Retrieval for Linguistic Question-Answering in European Portuguese: A Benchmark on Ciberdúvidas Da Língua Portuguesa

A novel benchmark framework for linguistic QA retrieval, empirical evidence supporting monolingual IR-specialised models, and insights into retrieval robustness under paraphrastic variation are included, enabling improved QA systems for specialised and low-resource environments.