Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Sen, Ma, Yinglei
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.15404
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914568019640320
author Yang, Sen
Ma, Yinglei
author_facet Yang, Sen
Ma, Yinglei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15404
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Capability Conditioned Scaffolding for Professional Human LLM Collaboration
Yang, Sen
Ma, Yinglei
Computation and Language
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.
title Capability Conditioned Scaffolding for Professional Human LLM Collaboration
topic Computation and Language
url https://arxiv.org/abs/2605.15404