LIU, Shuaitong; LI, Renjue; YU, Lijia; ZHANG, Lijun; LIU, Zhiming; JIN, Gaojie. BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 38, p. 32141–32149, 2026. DOI: 10.1609/aaai.v40i38.40486. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40486. Acesso em: 19 may. 2026.