Xuhao Hu, Peng Wang 0095, Xiaoya Lu, Dongrui Liu, Xuanjing Huang 0001, Jing Shao. LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 9348-9372, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.