A documentation format based on literate programming is claimed to improve LLM code generation, but the experiments show only toy-level success/failure results and a single RepoBench function.
If an error occurs, developers can isolate it to that chunk and provide the LLM with focused feedback, minimizing the spread of mistakes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects
A documentation format based on literate programming is claimed to improve LLM code generation, but the experiments show only toy-level success/failure results and a single RepoBench function.