Larger and more instructable language models become less reliable

Authors: Lexin Zhou, Wout Schellaert, Fernando Martínez-Plumed, Yael Moros-Daval, Cèsar Ferri & José Hernández-Orallo

Published: 2024

Publication: Nature

Research paper: Larger and more instructable language models become less reliable

Institution: Universitat Politècnica de València,University of Cambridge,ValGRAI

Research Area: LLM reliability and evaluation, competency assessment

Discipline: Artificial Intelligence , Behavioral Science