Testuen analisia

English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts

Gehiago irakurriEnglish Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts -ri buruz

Critical Questions Generation: Motivation and Challenges

The development of Large Language Models (LLMs) has brought impressive performances on mitigation strategies against misinformation, such as counterargument generation. However, LLMs are still seriously hindered by outdated knowledge and by their tendency to generate hallucinated content. In order to circumvent these issues, we propose a new task, namely, Critical Questions Generation, consisting of processing an argumentative text to generate the critical questions (CQs) raised by it.

Gehiago irakurriCritical Questions Generation: Motivation and Challenges -ri buruz

MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering

Gehiago irakurriMedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering -ri buruz

Multi-label Discourse Function Classification of Lexical Bundles in Basque and Spanish via transformer-based models

Gehiago irakurriMulti-label Discourse Function Classification of Lexical Bundles in Basque and Spanish via transformer-based models -ri buruz

Ixa at RefutES 2024: Leveraging Language Models for Counter Narrative Generation

Gehiago irakurriIxa at RefutES 2024: Leveraging Language Models for Counter Narrative Generation -ri buruz

A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation

Gehiago irakurriA LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation -ri buruz

Curriculum Learning for large language models in low-resource languages

Large language models (LLMs) are at the core of the current AI revolution, and have laid the groundwork for tremendous advancements in Natural Language Processing. Building LLMs require huge amounts of data, which is not available for low resource languages. As a result, LLMs shine in high-resource languages like English, but lag behind in many others, especially in those where training resources are scarce, including many regional languages in Europe. The data scarcity problem is usually alleviated by augmenting the training corpora in the target

Gehiago irakurriCurriculum Learning for large language models in low-resource languages -ri buruz

Towards Reliable E2R Texts: A Proposal for Standardized Evaluation Practices

Gehiago irakurriTowards Reliable E2R Texts: A Proposal for Standardized Evaluation Practices -ri buruz

Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques

Gehiago irakurriArgument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques -ri buruz

Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation

Counter Narratives (CNs) are non-negative textual responses to Hate Speech (HS) aiming at defusing online hatred and mitigating its spreading across media. Despite the recent increase in HS content posted online, research on automatic CN generation has been relatively scarce and predominantly focused on English. In this paper, we present CONAN-EUS, a new Basque and Spanish dataset for CN generation developed by means of Machine Translation (MT) and professional post-edition.

Gehiago irakurriBasque and Spanish Counter Narrative Generation: Data Creation and Evaluation -ri buruz

Hizkuntzak

Nor gara?

Zer egiten dugu?

Beste batzuk