safety
More Benign-Looking Data Revealed More of the Teacher
Scaling off-task generated data made an induced teacher trait easier to recover in the student.
Summary
Scaling off-task generated data made an induced teacher trait easier to recover in the student.
Across model families and trait settings, the target behavior generally strengthened with more independent distillation data even when examples never named it, motivating trait-aware curation and evaluation.
Why it matters
Scaling off-task generated data made an induced teacher trait easier to recover in the student.
Limits and context
No additional limitation was separately recorded.
Key claims
Scaling off-task generated data made an induced teacher trait easier to recover in the student.
Evidence: source-2026-08-29-021
Sources
- arXiv preprint 2608.26958arXiv · primary research
Corrections
No corrections have been recorded for this story.