LLMs implement both attention-based suppression and constructive representations for negation, with construction dominant, despite poor accuracy from late-layer attention shortcuts.
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
-
How Language Models Process Negation
LLMs implement both attention-based suppression and constructive representations for negation, with construction dominant, despite poor accuracy from late-layer attention shortcuts.