LLMs and VLMs exhibit grounding-dependent causal transfer in the OpenLock paradigm, requiring initial context-specific learning unlike humans who transfer structures from the first attempt.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Grounding Before Generalizing: How AI Differs from Humans in Causal Transfer
LLMs and VLMs exhibit grounding-dependent causal transfer in the OpenLock paradigm, requiring initial context-specific learning unlike humans who transfer structures from the first attempt.