2024-Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization) #78
skyleaworlder
started this conversation in
General
Replies: 1 comment
-
这篇文章做 “code summary”,与代码理解高度相关的任务。 具体来说,工作流如上图:(1) 输入原始代码;(2) 一系列用例集合;(3) 从待测项目中使用 BM25 挖掘一系列待测方法的用例 (exempler);(4) ASAP;(5,6) 与 LLM 交互。 对于每个 exempler,都有如下格式:
可见,该文的 prompt 构造是比较粗糙的。 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
https://dl.acm.org/doi/pdf/10.1145/3597503.3639183
Toufique Ahmed University of California, Davis Davis, California, USA tfahmed@ucdavis.edu
Kunal Suresh Pai University of California, Davis Davis, California, USA kunpai@ucdavis.edu
Premkumar Devanbu University of California, Davis Davis, California, USA ptdevanbu@ucdavis.edu
Earl T. Barr University College London & Google Brain London, UK e.barr@ucl.ac.uk
ICSE '24
from arxiv. I need to graduate on time!
Beta Was this translation helpful? Give feedback.
All reactions