Tag
This paper proposes Pruned BPE, a post-training method that prunes low-exposure tokens from a BPE vocabulary and reallocates slots to better-exposed candidates, reducing encoded length without increasing model-visible vocabulary size. Experiments on English and Chinese corpora show approximately 0.27–0.36% encoded length reduction over standard BPE.
MicroSpec is a training-free technique that builds compact, context-sensitive vocabularies on-the-fly to accelerate speculative decoding in large language models, reducing average vocabulary size by over 40x and achieving up to 1.32x end-to-end speedup over EAGLE-2.