AI RESEARCH
Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints
arXiv CS.AI
•
ArXi:2604.02699v1 Announce Type: cross A previous study reported that E-Prime (English without the verb "to be") selectively altered reasoning in language models, with cross-model correlations suggesting a structural signature tied to which vocabulary was removed. I designed a replication with active controls to test the proposed mechanism: cognitive restructuring through specific vocabulary-cognition mappings.