paper
Fodor and Pylyshyn's Systematicity Challenge Still Stands
paperactiveprovisional
fodor-and-pylyshyn-s-systematicity-challenge-still-stands-32e37750·1 events·first seen 2d agoAliases: Fodor and Pylyshyn's Systematicity Challenge Still Stands
Co-occurring entities
More like this (12)
Revisiting the Systematicity in Negation in the Era of In-Context LearningJerry FodorTuring completenessChain-of-Thought Self-ConsistencyWhen the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning ModelsBeyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning ModelsScaffold, Not Vocabulary? A Controlled, Two-Tier, Pre-Registered Study of a Popperian Code-Generation SkillCharXiv ReasoningFormalizing the Binding ProblemDynamic-Probabilistic Consistency GapOperadic consistency: a label-free signal for compositional reasoning failures in LLMszero-shot systematizer
Recent events (1)
Fodor and Pylyshyn's systematicity challenge to neural networks remains unmet, paper argues
A new arXiv preprint argues that recent claims that neural networks have met Fodor and Pylyshyn's systematicity challenge are premature. The authors specifically target Lake and Baroni's meta-learning for compositionality (MLC) protocol, showing it struggles with out-of-distribution rules and behaves unsystematically on many within-distribution problems. The paper concludes that the classical cognitive science challenge — that neural networks cannot explain systematic biconditional dependencies in language and thought — remains unresolved.