根据用户专业能力分级干预，避免盲目依赖AI判断。
Capability Conditioned Scaffolding for Professional Human LLM Collaboration
- 按专业强弱分类，动态调整AI干预策略。
- 实验显示不同能力模型下干预行为可精准切换。
- 适合需要可靠决策的专家型人机协作场景。
大语言模型个性化通常只适配用户偏好与风格，却忽略用户在不同领域评估能力的差异。这一局限可能导致‘专业领域漂移’——用户在无法有效评估的领域过度依赖AI推理。本文提出‘能力条件化支架’（Capability Conditioned Scaffolding），将专业领域划分为强、混合、弱三类，并基于结构化的用户能力画像来调控干预行为。在多个MMLU子集及四种LLM基座上的初步评估显示，干预行为能稳定响应能力画像：能力标签互换时出现类别反转，混合领域风险区实现选择性激活。结果表明，具备能力感知的支架机制可推动更可靠的专家级人机协作，超越仅关注风格的个性化。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。