Gizaki-Ordenagailu Elkarrekintza

Humanizing AI with language technology (HumanAIze)

The "Humanizing AI with Language Technology (HumanAIze)" project seeks to enhance Large Language Models (LLMs) to make them more human, reliable, and ethical by addressing weaknesses such as bias, cultural understanding, and reliability. Six research centers bring their expertise in areas such as multilingualism, anonymization, verification, and evaluation. A key approach is "reliable by design," implementing ethical and legal principles, data governance, human feedback, and sustainability.

CLARIAH-EUS-gArA

CLARIAH-EUS-gArA proiektuak Giza eta Gizarte Zientzien (GGZ) eta Adimen Artifizialaren (AA) arteko bi norabideko zubia eraiki nahi du. Horretarako elkarrizketa bidezko laguntzaile adimentsu bat garatuko du GGZetan ikertzeko. Kazetaritzaren domeinuan landuko dugu Latxa euskarazko Hizkuntza Eredu Handienaren (HEH) gaineko elkarrizketa-sistema RAG sistema batekin lagunduta.

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 However, LLMs are still seriously hindered by outdated knowledge and by their tendency to generate hallucinated content.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.

Orriak

RSS - Gizaki-Ordenagailu Elkarrekintza-rako harpidetza egin