Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates

Documenti analoghi

• Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs
  di: Sun, Zhihong, et al.
  Pubblicazione: (2024)
• Ensembling Large Language Models for Code Vulnerability Detection: An Empirical Evaluation
  di: Sun, Zhihong, et al.
  Pubblicazione: (2025)
• IRCoCo: Immediate Rewards-Guided Deep Reinforcement Learning for Code Completion
  di: Li, Bolun, et al.
  Pubblicazione: (2024)
• Knowledge-Aware Code Generation with Large Language Models
  di: Huang, Tao, et al.
  Pubblicazione: (2024)
• SemGuard: Real-Time Semantic Evaluator for Correcting LLM-Generated Code
  di: Wang, Qinglin, et al.
  Pubblicazione: (2025)