LLMs process negation using both attention-based suppression and constructive representation mechanisms (construction dominant), with late-layer attention shortcuts explaining poor accuracy on negation tasks.
Title resolution pending
2 Pith papers cite this work, alongside 9 external citations. Polarity classification is still indexing.
2
Pith papers citing it
9
external citations · OpenAlex
years
2026 2verdicts
UNVERDICTED 2representative citing papers
NSFL adapts t-norms and t-conorms to embedding spaces with NS-Delta and SQO to enable logical operations, reporting up to 81% mAP gains in retrieval tasks.
citing papers explorer
-
How Language Models Process Negation
LLMs process negation using both attention-based suppression and constructive representation mechanisms (construction dominant), with late-layer attention shortcuts explaining poor accuracy on negation tasks.
-
NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings
NSFL adapts t-norms and t-conorms to embedding spaces with NS-Delta and SQO to enable logical operations, reporting up to 81% mAP gains in retrieval tasks.