Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2023 IEEE/ACM 45th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 2023, pp. 324-325
- Issue Date:
- 2023-07-12
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 2209.05948v2.pdf | Submitted version | 2.73 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Currently large pre trained language models are widely applied in neural code completion systems Though large code models significantly outperform their smaller counterparts around 70 of displayed code completions from Copilot are not accepted by developers Being reviewed but not accepted their help to developer productivity is considerably limited Even worse considering the high cost of the large code models it is a huge waste of computing resources and energy To fill this significant gap we propose an early rejection mechanism to turn down low return prompts by foretelling the code completion qualities without sending them to the code completion system Furthermore we propose a lightweight Transformer based es timator to demonstrate the feasibility of the mechanism The experimental results show that the proposed estimator helps save 23 3 of computational cost measured in floating point operations for the code completion systems and 80 2 of rejected prompts lead to unhelpful completion
Please use this identifier to cite or link to this item: