Sep 13, 2022 · Motivated by this finding, we propose an early-rejection mechanism to turn down low-return prompts by foretelling the code completion qualities.
An early-rejection mechanism to turn down low-return prompts by foretelling the completion qualities without sending them to the LCM is proposed and a ...
Currently, large pre-trained models are widely applied in neural code completion systems, such as Github Copilot, aiXcoder, and TabNine.
Sep 13, 2022 · Motivated by this finding, we propose an early-rejection mechanism to turn down low-return prompts by foretelling the code completion qualities.
Currently, large pre-trained models are widely applied in neural code completion systems, such as Github Copilot, aiXcoder, and TabNine.
Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems ... Learning to Prevent Profitless Neural Code Completion.
Aug 16, 2024 · Motivated by this finding, we propose an early-rejection mechanism to turn down low-return prompts by foretelling the code completion qualities.
Missing: Profitless | Show results with:Profitless
Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion ... Readers: Everyone. Learning to Prevent Profitless Neural Code ...
from publication: Learning to Prevent Profitless Neural Code Completion | Currently, large pre-trained models are widely applied in neural code completion ...
Соавторы ; Learning to Prevent Profitless Neural Code Completion. Z Sun, X Du, F Song, S Wang, M Ni, L Li. arXiv preprint arXiv:2209.05948, 2022. 3, 2022.