SADIEKH, Sabrina; ERICHEVA, Elena; AGARWAL, Chirag. Polarity-Aware Probing for Quantifying Latent Alignment in Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 37896–37903, 2026. DOI: 10.1609/aaai.v40i44.41126. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41126. Acesso em: 25 may. 2026.