AAAI 2026technical0 citations

Obedience or Vigilance? How Large Language Models React to Malicious Multiple-Choice Options (Student Abstract)

Yow-Fu Liou, Yu-Chien Tang, An-Zi Yen

Abstract

When evaluating large language models (LLMs) for question answering tasks, a common protocol is multiple-choice question-answering (MCQA), where the model selects from a fixed set of choices. In contemporary robustness testing, researchers typically perturb instructions or introduce confusion into factual statements; however, model behavior also hinges on choice compliance: whether models remain within the canonical set A-D. We formalize this setting by asking whether the model continues to respect the interface

BibTeX
@inproceedings{aaai2026_obedienceorvigil,
  title = {Obedience or Vigilance? How Large Language Models React to Malicious Multiple-Choice Options (Student Abstract)},
  author = {Yow-Fu Liou and Yu-Chien Tang and An-Zi Yen},
  booktitle = {AAAI 2026},
  year = {2026}
}
Obedience or Vigilance? How Large Language Models React to Malicious Multiple-Choice Options (Student Abstract) · AAAI 2026