Self-Prompt: Gradient-guided discrete prompt optimization for code generation
Authors:
- Liangdongzheng ZhuLZLiangdongzheng Zhu
- Wenxi ZongWZWenxi Zong
- Yu TongYTYu Tong
- Ge ChenGCGe Chen
- Xiaofeng MouXMXiaofeng Mou
- Xiaojun LuXLXiaojun Lu
- Yi XuYXYi Xu
- 31 August 2026
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 706
Abstract
No abstract availableThis publication has 9 references indexed in Scilit:
- A Review of Prompt Engineering Techniques for Large Language ModelsInternational Journal of Human–Computer Interaction, 2025
- CSGrasp: Category-Level Semantically-Aware Grasping MethodIEEE Transactions on Industrial Electronics, 2025
- Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language ModelsACM Transactions on Software Engineering and Methodology, 2025
- Evidence-based Multi-Feature Fusion for Adversarial RobustnessIEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
- Deep learning-based software engineering: progress, challenges, and opportunitiesScience China Information Sciences, 2024
- PATNAS: A Path-Based Training-Free Neural Architecture SearchIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Transformer in reinforcement learning for decision-making: a surveyFrontiers of Information Technology & Electronic Engineering, 2024
- CodeRL: Mastering Code Generation Through Pretrained Models and Deep Reinforcement Learning2022
- Training Language Models to Follow Instructions with Human Feedback2022