Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
Not assessedPlan blockedMeasurementclaim_t3_sd_fkl
Mid-training ablation results for Switch Distillation with FKL relative difference across Reasoning, Factual Recall, and Knowledge task groups.
Source: source_paper:Table 3, Page 9
Reported and observed measurements
delta_percentage_points
t3_sd_fkl_reasoning
Reported -2.9 percentage_points
Observed — percentage_points
delta_percentage_points
t3_sd_fkl_factual_recall
Reported -0.2 percentage_points
Observed — percentage_points
delta_percentage_points
t3_sd_fkl_knowledge
Reported -1.4 percentage_points
Observed — percentage_points
Assessments (0)
No immutable Assessment has been published for this Claim yet.
Runs (0)
No execution has been linked to this Claim yet.