Jun 16, 2023 · In this paper, we analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS. We find that ...

Nov 22, 2023 · We study self-repair for code generation, finding that gains are often marginal and quite inconsistent, and offer several insights as to why.

Our results suggest that self-repair is not a silver bullet for code generation, and that current models are held back by their inability to reliably produce ...

It contains source code used to run the experiments; the resulting data; as well as scripts to replicate the data analysis and figures from the paper.

Analysis of Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS finds that when the cost of carrying ...

Feb 2, 2024 · with feedback from human participants suggests that even for the strongest models, self-repair still lags far behind what can be achieved with ...

Feb 5, 2024 · Is Self-Repair a Silver Bullet for Code Generation? Large language models have shown remarkable aptitude in code generation, but still struggle ...

Is Self-Repair a Silver Bullet for Code Generation?. Olausson, T. X., Inala, J. P., Wang, C., Gao, J., & Solar-Lezama, A. In The Twelfth International ...

Is Self-Repair a Silver Bullet for Code Generation? ... We hypothesize that this is because self-repair is bottlenecked by the model's ability to provide feedback ...

Missing: Silver Bullet