Verified65% confidenceFactExact time
The Byte Pair Encoding (BPE) tokenization algorithm was originally introduced by OpenAI in GPT-2, splitting text into subword units by iteratively merging high-frequency character pairs.
3
Sources
65%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
Related Claims
VerifiedGPT-series models use the Byte Pair Encoding (BPE) algorithm to segment text into tokens.82% similarUnverifiedBPE（字节对编码）算法最初是一种数据压缩算法，后被引入NLP领域并应用于GPT、Claude等主流大语言模型的分词器设计80% similarUnverifiedOpenAI 使用基于字节对编码（BPE）的 tiktoken 分词器将文本切分为 Token79% similarUnverifiedOpenAI uses the BPE (Byte Pair Encoding) algorithm for tokenization, while Google's SentencePiece adopts a language-agnostic tokenization method trained directly on raw text.78% similarVerifiedThe BPE algorithm originates from the field of data compression and builds a vocabulary by iteratively merging high-frequency character pairs.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/563277API
curl https://kongchang.com/api/v1/knowledge/claims/563277MCP
get_claim(id=563277)