
Enhancing large language models (LLMs) with execution-based feedback improves code generation accuracy for data science tasks.


coremsg

grounding-data-science-code-generation-with-input-output-specifications-enhancing-llms-with-execution-based-feedback


Grounding Data Science Code Generation with Input-Output Specifications: Enhancing LLMs with Execution-Based Feedback


title_rewrite


Pre-trained code language models struggle with self-refinement, but Cycle framework enhances self-refinement capability, improving code generation performance.


learning-to-self-refine-code-generation-with-cycle-framework


Learning to Self-Refine Code Generation with Cycle Framework
