LI, C.; FLANIGAN, J. Task Contamination: Language Models May Not Be Few-Shot Anymore. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 38, n. 16, p. 18471-18480, 2024. DOI: 10.1609/aaai.v38i16.29808. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/29808. Acesso em: 11 sep. 2024.