Gold-token probability, gradient attenuation relative to NTP, and factual recall deficits under KD hold consistently for OLMo-2 1B and 13B Instruct teachers. · CiteArk
Not assessedPlan blockedFindingclaim_fig11_factual_recall_kd_analysis_1b_13b
Gold-token probability, gradient attenuation relative to NTP, and factual recall deficits under KD hold consistently for OLMo-2 1B and 13B Instruct teachers.
Source: source_paper:Figure 11, Page 30
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.