Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
Not assessedPlan blockedMeasurementclaim_t3_sd_baseline
Mid-training ablation results for Switch Distillation absolute macro-averages across Reasoning, Factual Recall, and Knowledge task groups.
Source: source_paper:Table 3, Page 9
Reported and observed measurements
macro_average
t3_sd_baseline_reasoning
Reported 44.7 percentage_points
Observed — percentage_points
macro_average
t3_sd_baseline_factual_recall
Reported 29.3 percentage_points
Observed — percentage_points
macro_average
t3_sd_baseline_knowledge
Reported 49.3 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.