Summary of A Survey on Large Language Models For Code Generation, by Juyong Jiang et al.
A Survey on Large Language Models for Code Generation
by Juyong Jiang, Fan Wang, Jiasi Shen, Sungju Kim, Sunghun Kim
First submitted to arxiv on: 1 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A comprehensive literature review on Large Language Models (LLMs) for code generation has been lacking, despite their remarkable advancements across various code-related tasks. This survey aims to bridge this gap by providing a systematic review of recent developments, categorizing them using a new taxonomy. The review covers aspects such as data curation, performance evaluation, ethical implications, environmental impact, and real-world applications. It also presents an empirical comparison using the HumanEval, MBPP, and BigCodeBench benchmarks to highlight progressive enhancements in LLM capabilities. Critical challenges and promising opportunities are identified regarding the gap between academia and practical development. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models (LLMs) can generate code from natural language descriptions! This is super cool because it can help software developers write code faster. Researchers have been working on this for a while, but they haven’t done a big review of all their work yet. This paper does that review and finds out what’s worked well and what hasn’t. It also talks about the challenges and opportunities in using LLMs for code generation. The authors even made a special page on GitHub where you can find more information! |
