Large language models synthesize Python code from descriptions with log-linear scaling in performance, reaching 59.6% on MBPP via few-shot prompting and 83.8% on MathQA-Python after fine-tuning, while human feedback halves error rates but models fail at predicting program outputs.
If they use strings as enums, define these values in the natural language question
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.PL 1years
2021 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Program Synthesis with Large Language Models
Large language models synthesize Python code from descriptions with log-linear scaling in performance, reaching 59.6% on MBPP via few-shot prompting and 83.8% on MathQA-Python after fine-tuning, while human feedback halves error rates but models fail at predicting program outputs.