AINeutralarXiv – CS AI · Apr 66/10
🧠
Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints
A replication study found that simple vocabulary constraints like banning filler words ('very', 'just') improved AI reasoning performance more than complex linguistic restrictions like E-Prime. The research suggests any constraint that disrupts default generation patterns acts as an output regularizer, with shallow constraints being most effective.