Skip to content
conftrace_

data mixture inference

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

token frequency analysis (1) pretraining data (1) large language model (1) membership inference attack (1) membership inference (1) linear program (1) training data composition (1) bpe tokenizer (1) data mixture (1) token frequency (1)

Papers

Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions NeurIPS 2024