Papers by Pablo Rodríguez
High-quality argumentative information in low resources approaches improve counter-narrative generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that fine-tuning improves the performance of language models . large language models generate acceptable texts in a number of scenarios, a study shows . |
| Approach: | They show that fine-tuning improves the task of hate speech counter-narrative generation . they provide a subset of arguments and a good base model is required for the fine-uning to have a positive impact. |
| Outcome: | The proposed model produces counter-narratives that are as satisfactory as the whole set. |
Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to remarkable improvements in language understanding and text generation. |
| Approach: | They propose a framework to evaluate large language models for underrepresented languages . they examine CPT strategies for languages with limited representation in multilingual models . |
| Outcome: | The proposed evaluation framework is based on the case of Galician language . it assesses trade-offs between linguistic enrichment and task-solving capabilities . |