AI RESEARCH
Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs
arXiv CS.CL
•
ArXi:2605.04665v1 Announce Type: new When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that they often do not, even at temperature zero.