Skip to content
arXiv cs.LG · Papers

Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override

arXiv:2606.07555v4 Announce Type: replace-cross Abstract: Glossaries, technical specifications, and system prompts routinely ask language models to use familiar words in unfamiliar ways. The instruction competes with what the word already means, and even when it wins, the pretrained prior keeps operating underneath. We