Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable
Ranking
Overall
83
Content
100
Popularity
42
Observed public metrics from 1 member.
Merged summary
TL;DR - Scaling model-generated distillation datasets can amplify subtle teacher-specific traits in students, even when the training examples are off-task and never explicitly mention those traits. This creates a latent behavior-transfer risk that conventional data screening may miss.
- Larger independent off-task datasets made an induced teacher trait more detectable in students compared with matched no-trait controls.
- Scaling either amplified an already favored target trait or shifted behavior from a related alternative toward the intended trait.
- Learned LoRA updates showed a parallel scaling trend, with effects observed across model families, trait types, multi-trait settings, and cross-model transfer.
- The findings motivate trait-aware curation and evaluation of synthetic distillation data, including data that appears benign.
Sources (1)
Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - Scaling model-generated distillation datasets can amplify subtle teacher-specific traits in students, even when the training examples are off-task and never explicitly mention those traits. This creates a latent behavior-transfer risk that conventional data screening may miss.
- Larger independent off-task datasets made an induced teacher trait more detectable in students compared with matched no-trait controls.
- Scaling either amplified an already favored target trait or shifted behavior from a related alternative toward the intended trait.
- Learned LoRA updates showed a parallel scaling trend, with effects observed across model families, trait types, multi-trait settings, and cross-model transfer.
- The findings motivate trait-aware curation and evaluation of synthetic distillation data, including data that appears benign.