Obedience or Vigilance? How Large Language Models React to Malicious Multiple-Choice Options
Published in AAAI 2026 Student Abstract, 2026
Authors: Yow-Fu Liou, Yu-Chien Tang, An-Zi Yen
Yu-Chien Tang
Ph.D. student in CS at National Yang Ming Chiao Tung University, Taiwan. My research interests include LLMs, information retrieval, question answering, and multimodal assistants.
- Hsinchu, Taiwan
- National Yang Ming Chiao Tung University
- Google Scholar
- ORCID
- GitHub
- X (formerly Twitter)