◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Shasha Mo

2 papers

No researched profile yet.

papers

Publications (2)

cs.CL2024

LBPE: Long-token-first Tokenization to Improve Large Language Models

Haoran Lian, Yizhe Xiong, Zijia Lin +5

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its…

cs.CL2024

Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal

Haoran Lian, Yizhe Xiong, Jianwei Niu +7

Byte Pair Encoding (BPE) serves as a foundation method for text tokenization in the Natural Language Processing (NLP) field. Despite its wide adoption, the original BPE algorithm h…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Sign in
  • Library
  • Chat
Data
  • arXiv.org
  • Latest RSS
Not affiliated with arXiv