AINeutralarXiv – CS AI · 3h ago6/10
🧠
Sense Representations Are Inducible Interfaces
Researchers introduce ACROS, a method that adds explicit sense representations (per-token meaning decompositions) to frozen pretrained language models without retraining. The technique achieves competitive results in word-sense disambiguation, lexical steering, and cross-lingual adaptation, positioning sense representations as a practical interface for existing models.