Pablo Gamallo Otero

Also published as: Pablo Gamallo Otero


2024

pdf bib
Leveraging Advanced Prompting Strategies in LLaMA3-8B for Enhanced Hyperpartisan News Detection
Michele Maggini | Pablo Gamallo Otero
Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)

This paper explores advanced prompting strategies for hyperpartisan news detection using the LLaMA3-8b-Instruct model, an open-source LLM developed by Meta AI. We evaluate zero-shot, few-shot, and Chain-of-Thought (CoT) techniques on two datasets: SemEval-2019 Task 4 and a headline-specific corpus. Collaborating with a political science expert, we incorporate domain-specific knowledge and structured reasoning steps into our prompts, particularly for the CoT approach. Our findings reveal that zero-shot prompting, especially with general prompts, consistently outperforms other techniques across both datasets. This unexpected result challenges assumptions about the superiority of few-shot and CoT methods in specialized tasks. We discuss the implications of these findings for ICL in political text analysis and suggest directions for future research in leveraging large language models for nuanced content classification tasks.

pdf bib
Exploring the effects of vocabulary size in neural machine translation: Galician as a target language
Daniel Bardanca Outeirinho | Pablo Gamallo Otero | Iria de-Dios-Flores | José Ramom Pichel Campos
Proceedings of the 16th International Conference on Computational Processing of Portuguese - Vol. 1

2007

pdf bib
Learning bilingual lexicons from comparable English and Spanish corpora
Pablo Gamallo Otero
Proceedings of Machine Translation Summit XI: Papers

2005

pdf bib
Extraction of translation equivalents from parallel corpora using sense-sensitive contexts
Pablo Gamallo Otero
Proceedings of the 10th EAMT Conference: Practical applications of machine translation