QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
Springer-Verlag (1987)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proves equivalence of big-step and small-step Horn clause derivations and supplies a transformation to convert any clause set into one inheriting a chosen derivation behavior.
citing papers explorer
-
Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
-
Big-step and small-step Horn clause derivations applied to operational semantics
Proves equivalence of big-step and small-step Horn clause derivations and supplies a transformation to convert any clause set into one inheriting a chosen derivation behavior.