Reverse KL Distillation (RKD, alpha=0.5) downstream evaluation performance after mid-training with OLMo-2 7B Instruct teacher.

Reverse KL Distillation (RKD, alpha=0.5) downstream evaluation performance after mid-training with OLMo-2 7B Instruct teacher. · CiteArk

Measurement results

0/15 assessed

0 supported0 disputed or conflicting15 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Reported	Latest observation	Evidence judgment
62.1 percentage_points	—	Not assessed
46.2 percentage_points	—	Not assessed
39.2 percentage_points	—	Not assessed
31.6 percentage_points	—	Not assessed
43.1 percentage_points	—	Not assessed
10.4 percentage_points	—	Not assessed
53.1 percentage_points	—	Not assessed
24.1 percentage_points	—	Not assessed
8.4 percentage_points	—	Not assessed
50.1 percentage_points	—	Not assessed
18.9 percentage_points	—	Not assessed
62.5 percentage_points	—	Not assessed

Reverse KL Distillation (RKD, alpha=0.5) downstream evaluation performance after mid-training with OLMo-2 7B Instruct teacher.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results