INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair

Benchmark Model Rank Results
code-generation-on-mbppGPT-3.5 Turbo + INTERVENOR#21Accuracy: 69.8
code-generation-on-mbppGPT-3.5 Turbo (few-shot)#64Accuracy: 45.4
code-generation-on-mbppGPT-3.5 Turbo (0-shot)#72Accuracy: 39.8