Papers by Damián Furman
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. |
MessIRve: A Large-Scale Spanish Information Retrieval Dataset (2025.emnlp-main)
Copied to clipboard
Francisco Valentini, Viviana Cotik, Damián Furman, Ivan Bercovich, Edgar Altszyler, Juan Manuel Pérez
| Challenge: | Information retrieval (IR) is the task of finding relevant documents in response to a user query. |
| Approach: | They propose a large-scale Spanish IR dataset with almost 700,000 queries from Google’s autocomplete API and relevant documents sourced from Wikipedia. |
| Outcome: | The proposed dataset covers a wide variety of topics, unlike smaller datasets. |