Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation

2026-09-12

AI Summary

研究通过无显式推理监督的专家模型训练方法，利用学生蒸馏作为探针观察隐含轨迹分布，揭示了调整选择直接影响传递给下游模型的隐式监督。

Abstract

Specialist distillation effectively transfers domain expertise to student models via teacher-generated reasoning trajectories. However, when these specialists are trained solely on question--answer pairs without explicit reasoning supervision, what governs the trajectories they generate? In this work, we show that specialist optimization implicitly selects from this latent trajectory space. To isolate and observe this latent distribution, we leverage student distillation not as a downstream goal, but as an agnostic probe---since students inherit no parameterization or optimization constraints from the specialist, inheriting only the sampled trajectories themselves. Through this probe, our empirical analysis unveils a tight governing relationship: across 27 specialist--student pairings, their specialization--generalization profiles correlate exceptionally strongly. Crucially, explicitly controlling the specialist's distributional drift systematically shifts both the teacher and its distilled student along a controllable trade-off between domain precision and general-capability retention. Across chemistry, physics, and multilingual settings, distilled students systematically reflect these specialist-induced profiles, even across divergent model families. Our findings establish a new view of specialist training: when gold reasoning is absent, tuning choices directly control the latent supervision passed to downstream models.

Problem

• specialist distillation
• reasoning trajectories
• domain expertise
• latent trajectory space
• student distillation

Innovation

• specialist distillation
• latent trajectory space
• student distillation as probe
• specialization-generalization trade-off