Wait, That's Not an Option: LLM Robustness with Incorrect Multiple-Choice Options

Gracjan Góral, Emilia Wiśnios, Piotr Sankowski, Paweł Budzianowski

Keywords: LLMs, Reflective Judgment, Alignment, Instruction Following, Misleading Instructions

Abstract:

Decision-making under full alignment requires balancing between reasoning and faithfulness - a challenge for large language models (LLMs). This study explores whether LLMs prioritize following instructions over reasoning and truth when given "misleading" instructions, such as "Respond solely with A or B", even when neither option is correct. We introduce a new metric called "reflective judgment", which sheds new light on the relationship between the pre-training and post-training alignment schemes. In tasks ranging from basic arithmetic to domain-specific assessments, models like GPT-4o, o1-mini, or Claude 3 Opus adhered to instructions correctly but failed to reflect on the validity of the provided options. Contrary, models from the Llama 3.1 family (8B, 70B, 405B) or base Qwen2.5 (7B, 14B, 32B) families exhibit improved refusal rates with size, indicating a scaling effect.
We also observed that alignment techniques, though intended to enhance reasoning, sometimes weakened the models' ability to reject incorrect instructions, leading them to follow flawed prompts uncritically. Finally, we have also conducted a parallel human study revealing similar patterns in human behavior and annotations. We highlight how popular RLHF datasets might disrupt either training or evaluation due to annotations exhibiting poor reflective judgement.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11852