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.
Mapping the Neuro-Symbolic
2 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
2
Pith papers citing it
3
external citations · external index
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Symbol grounding is necessary but insufficient for compositional generalization; explicit multi-step reasoning training is required for zero-shot performance on novel entities, relations, and rule compositions.
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.
-
Grounding vs. Compositionality: On the Non-Complementarity of Reasoning in Neuro-Symbolic Systems
Symbol grounding is necessary but insufficient for compositional generalization; explicit multi-step reasoning training is required for zero-shot performance on novel entities, relations, and rule compositions.