Line of inquiry
Inquiring lines›How do architecture and constraint…›How can systems understand user in…›this line of inquiry
How are knowledge and reasoning functionally separated in neural network architecture?
A broader line of inquiry — a family of 45 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 45
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Why do knowledge and reasoning train in different network layers?
- Why do higher network layers capture procedural knowledge but lower layers store facts?
- How do retrieval heads interact with layer-level separation of knowledge and reasoning?
- Why does knowledge storage separate from reasoning circuits in neural networks?
- How do procedural versus factual knowledge differ in pretraining versus fine-tuning?
- What separates knowledge from reasoning in neural network layers?
- Does model scaling improve knowledge storage faster than reasoning ability?
- What is the difference between procedural knowledge and factual retrieval in reasoning?
- How do hierarchical architectures separate planning from retrieval differently than flat ones?
- How do knowledge layers differ functionally from reasoning layers in networks?
- How do knowledge and reasoning circuits interfere in the same neural network?
- How should we rethink the symbolism versus connectionism debate in light of LLMs?
- How many document exposures does procedural knowledge versus factual information require?
- Why does the same recalled information lead to different reasoning conclusions?
- What can agents learn from the brain's complementary learning systems?
- How does the knowing-doing gap widen as tasks become more complex?
- Are traditional cognitive theories missing interaction effects between mechanisms?
- Why does reasoning transfer across different numbers but factual recall does not?
- What makes knowledge editing different from simply finding where facts are stored?
- How does treating cognition as computation reshape education and work?
- How do single-ordering encyclopedic systems limit ways of knowing?
- What explains the contextual variability of knowledge in transformers?
- What role do ontologies play in AI understanding context?
- What makes language an effective parameterization for procedural knowledge?
- Why does grokking reveal the shift from memorization to genuine understanding?
- What makes procedural knowledge better than factual knowledge for authoring tasks?
- What's the difference between representing world facts and generating world mechanisms?
- How does dual-rate learning separate episodic and procedural memory in neural networks?
- How do early layers preserve unbiased information while late layers conform?
- How does cognitive fit theory explain why different tasks need different knowledge structures?
- How do biological brains organize computation across different cortical timescales?
- How do hierarchical knowledge layers capture different types of narrative information?
- What happens when you tightly couple two representations together?
- What distinguishes new associations from existing ones at the computational level?
- Why does the generation-verification gap disappear for factual recall tasks?
- Can a single architecture represent both physical and mental possibility spaces?
- What does a machine-legible ontology look like in practice inside enterprises?
- Can episodic and semantic memory split the same way emotion and facts do?
- What makes knowledge seeding equivalent to hippocampal replay in the brain?
- How does co-activation shape which memories become linked together?
- How does anomalous knowledge state connect to the gulf of envisioning?
- How does the hippocampus bind disparate elements without storing everything itself?
- How does computational split-brain syndrome differ from ordinary knowledge gaps?
- How does upward distillation transfer knowledge from smaller to larger networks?
- What role does curriculum design play in reasoning emergence?