Capability Conditioned Scaffolding for Professional Human LLM Collaboration
For professional human-AI collaboration, this work addresses the problem of users over-relying on AI in domains they cannot evaluate, offering a more reliable alternative to stylistic personalization.
The paper introduces Capability Conditioned Scaffolding, a framework that partitions user expertise into strong, mixed, and weak domains and conditions LLM intervention behavior on structured capability profiles. Pilot evaluation across MMLU subsets and four LLM substrates shows consistent profile-conditioned intervention behavior, including categorical inversion under profile swapping and selective activation in mixed domain risk zones.
Large language model personalization typically adapts outputs to user preferences and style but does not account for differences in user evaluation capacity across domains of expertise. This limitation can encourage Professional Domain Drift, where users rely on AI generated reasoning in domains they cannot reliably evaluate. We introduce Capability Conditioned Scaffolding, a typed framework that partitions expertise into strong, mixed, and weak domains and conditions intervention behavior on structured capability profiles. A pilot evaluation across multiple MMLU subsets and four LLM substrates shows consistent profile conditioned intervention behavior, including categorical inversion under profile swapping and selective activation in mixed domain risk zones. These findings suggest that capability aware scaffolding can support more reliable professional human AI collaboration beyond stylistic personalization.