algo
now
.net
AI scenarios
practice areas
algo puzzles
Legacy reference
lessons
atlas
problems
fields
legacy
/
algorithms
/
Perplexity evaluation
Perplexity evaluation
Pairings in the atlas
Held-out token likelihood
standard
Model output evaluation
llm-training-alignment
Rivals: other methods for the same problems
BERTScore
BLEU scoring
LLM-as-judge
Pass-at-k estimation
ROUGE scoring
Where it sits
llm-training-alignment
·
Machine Learning & AI