BPE tokenizers can leak whether a dataset was in training
RTAM-Fusion uses rare-token mass and fewer shadow tokenizers to beat Vocabulary Overlap on a membership benchmark.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
RTAM-Fusion uses rare-token mass and fewer shadow tokenizers to beat Vocabulary Overlap on a membership benchmark.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views