Median cross-entropy tracks language model task performance more reliably than mean cross-entropy during synthetic fact-learning SFT and top-K distillation.
?”. Examples include“Complete: Above Nimbusglade floats ___
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Mean CE Fails: Median CE Can Better Track Language Model Quality
Median cross-entropy tracks language model task performance more reliably than mean cross-entropy during synthetic fact-learning SFT and top-K distillation.