SyncAI.news, a Varaisys broadcasting
When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints
YC

Yuheng Chen, Zhiyu Wu, Bowen Cheng, Yihang Wu, Tetsuro Takahashi

· 1 min read

ResearcharXiv cs.CL

When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints

arXiv:2604.16916v2 Announce Type: replace Abstract: We identify and systematically characterize a class of task-structural alignment failures in large language models (LLMs): even when the harmful intent remains unchanged, changing the task presentation and output constraints can substantially alter model safety behavior. Specifically, when a harmful request is reformulated as a forced-choice multiple-choice question (MCQ) in which all options are harmful and no refusal option is provided, some models that refuse the equivalent open-ended query instead select, prefer, or justify a harmful option. We evaluate 14 proprietary and open-source models on a bilingual Chinese-English human-authored dataset covering five harm categories, together with 900 model-generated Chinese adversarial MCQs. On human-authored data, attack success rate (ASR) increases sharply as prompts shift from open-ended queries to explicit forced-choice formats, typically peaking under intermediate levels of choice constraint. Model-generated Chinese MCQs further weaken or eliminate the recovery regime observed on human-authored data, driving ASR close to saturation for multiple models. The observed transfer patterns are consistent with stronger generators producing more difficult or boundary-adjacent MCQs, although other properties of the generated inputs may also contribute. We also find that adding an explicit refusal option or a safety preamble substantially reduces ASR for several high-capability models, often to near-zero levels, although their effectiveness varies across target models. These findings suggest that safety evaluations centered on open-ended generation may underestimate risks in structured deployment settings, and that task structure should be treated as an important and diagnosable dimension of safety evaluation and alignment training.

Original source

This story was published by arXiv cs.CL and written by Yuheng Chen, Zhiyu Wu, Bowen Cheng, Yihang Wu, Tetsuro Takahashi. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News