Empirical tests on software engineering tasks show Chinese prompts do not reduce token usage or improve success rates over English for LLM coding.
Sentence- piece: A simple and language independent sub- word tokenizer and detokenizer for neural text processing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate
Empirical tests on software engineering tasks show Chinese prompts do not reduce token usage or improve success rates over English for LLM coding.