Description and contribution
An experimental study of language models acting as domain experts in validation tasks, using questions with controlled and potentially biased contexts.
Bibliographic reference
Carlos Badenes Olmedo; Esteban García Cuesta; Alejandro Sanchez Gonzalez; Oscar Corcho. "Leveraging Large Language Models (LLMs) as Domain Experts in a Validation Process". En: Poster Proceedings of the 40th Annual Conference of the Spanish Association for Natural Language Processing 2024 (SEPLN-P 2024). 3846, CEUR Workshop Proceedings, 2024. Disponible en Internet en: <https://ceur-ws.org/Vol-3846/paper13.pdf>. ISSN 1613-0073