Documentdetail
ID kaart

oai:arXiv.org:2408.05715

Onderwerp
Computer Science - Artificial Inte... Computer Science - Software Engine...
Auteur
Lyu, Zhi-Cun Li, Xin-Ye Xie, Zheng Li, Ming
Categorie

Computer Science

Jaar

2024

vermelding datum

14-08-2024

Trefwoorden
code correct science computer top generation
Metriek

Beschrijving

Code generation has been greatly enhanced by the profound advancements in Large Language Models (LLMs) recently.

Nevertheless, such LLM-based code generation approaches still struggle to generate error-free code in a few tries when faced with complex problems.

To address this, the prevailing strategy is to sample a huge number of candidate programs, with the hope of any one in them could work.

However, users of code generation systems usually expect to find a correct program by reviewing or testing only a small number of code candidates.

Otherwise, the system would be unhelpful.

In this paper, we propose Top Pass, a code ranking approach that identifies potential correct solutions from a large number of candidates.

Top Pass directly optimizes the pass@k loss function, enhancing the quality at the top of the candidate list.

This enables the user to find the correct solution within as few tries as possible.

Experimental results on four benchmarks indicate that our Top Pass method enhances the usability of code generation models by producing better ranking results, particularly achieving a 32.9\% relative improvement in pass@1 on CodeContests when compared to the state-of-the-art ranking method.

;Comment: Accepted by Frontier of Computer Science

Lyu, Zhi-Cun,Li, Xin-Ye,Xie, Zheng,Li, Ming, 2024, Top Pass: Improve Code Generation by Pass@k-Maximized Code Ranking

Document

Openen

Delen

Bron

Artikelen aanbevolen door ES/IODE AI

Batoclimab as induction and maintenance therapy in patients with myasthenia gravis: rationale and study design of a phase 3 clinical trial
gravis myasthenia study clinical phase baseline improvement mg-adl 340 week trial placebo period mg maintenance qw