Line of inquiry
Inquiring lines›How should agents manage and coord…›How effectively can inference-time…›this line of inquiry
How do neural networks separate factual knowledge from reasoning abilities?
A broader line of inquiry — a family of 29 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 29
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?
- What separates knowledge from reasoning in neural network layers?
- How do retrieval heads interact with layer-level separation of knowledge and reasoning?
- What is the difference between procedural knowledge and factual retrieval in reasoning?
- How do knowledge layers differ functionally from reasoning layers in networks?
- How do procedural versus factual knowledge differ in pretraining versus fine-tuning?
- What makes procedural knowledge in documents generalize better than facts?
- How do we distinguish knowledge encoding from knowledge usage in models?
- Do reasoning systems reuse cognitive structures across unrelated topics?
- Why does knowledge storage separate from reasoning circuits in neural networks?
- What makes knowledge-rich specialized domains structurally different from general reasoning tasks?
- When does knowledge activation fail across different model architectures?
- Does knowledge structure matter more than knowledge volume for model training?
- How does cross-domain reasoning transfer differ from domain-specific knowledge transfer?
- How many document exposures does procedural knowledge versus factual information require?
- How do knowledge and reasoning circuits interfere in the same neural network?
- How does the knowing-doing gap widen as tasks become more complex?
- Why does contextual judgment matter more in law and medicine than in mathematics?
- What distinguishes conceptual understanding from statistical pattern matching in models?
- Can pruning half of LLM layers affect knowledge retrieval performance?
- How do verbose and concise reasoning occupy different regions in activation space?
- How do LLMs compress specific expert knowledge into median abstraction?
- What makes task alignment more fragile than underlying knowledge retention?
- Why do medical and mathematical tasks require fundamentally different model capabilities?
- How does cognitive fit theory explain why different tasks need different knowledge structures?
- How do hierarchical knowledge layers capture different types of narrative information?
- How does computational split-brain syndrome differ from ordinary knowledge gaps?
- Why do two experts with identical knowledge produce different outcomes in the same situation?