LLMs exhibit compartmentalization by learning separate internal representations for equivalent concepts presented differently, which reduces sample efficiency and resists unification even with synthetic parallel data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Language models struggle with compartmentalization
LLMs exhibit compartmentalization by learning separate internal representations for equivalent concepts presented differently, which reduces sample efficiency and resists unification even with synthetic parallel data.