Creative and Correct: Requesting Diverse Code Solutions from AI Foundation Models

March 20, 2024 Β· Declared Dead Β· πŸ› 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering (Forge) Conference Acronym:

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Scott Blyth, Markus Wagner, Christoph Treude arXiv ID 2403.13259 Category cs.SE: Software Engineering Citations 3 Venue 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering (Forge) Conference Acronym: Last Checked 4 months ago
Abstract
AI foundation models have the capability to produce a wide array of responses to a single prompt, a feature that is highly beneficial in software engineering to generate diverse code solutions. However, this advantage introduces a significant trade-off between diversity and correctness. In software engineering tasks, diversity is key to exploring design spaces and fostering creativity, but the practical value of these solutions is heavily dependent on their correctness. Our study systematically investigates this trade-off using experiments with HumanEval tasks, exploring various parameter settings and prompting strategies. We assess the diversity of code solutions using similarity metrics from the code clone community. The study identifies combinations of parameters and strategies that strike an optimal balance between diversity and correctness, situated on the Pareto front of this trade-off space. These findings offer valuable insights for software engineers on how to effectively use AI foundation models to generate code solutions that are diverse and accurate.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted