Few-shot Training Llms For Project-specific Code-summarization | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A collection of research papers on LLMs.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Few-shot Training Llms For Project-specific Code-summarization

Toufique Ahmed, Premkumar Devanbu . Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering 2022 – 129 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization Few Shot Interdisciplinary Approaches Llm For Code Model Architecture Multimodal Semantic Representation Training Techniques

Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A particularly exciting aspect of LLMs is their knack for few-shot and zero-shot learning: they can learn to perform a task with very few examples. Few-shotting has particular synergies in software engineering, where there are a lot of phenomena (identifier names, APIs, terminology, coding patterns) that are known to be highly project-specific. However, project-specific data can be quite limited, especially early in the history of a project; thus the few-shot learning capacity of LLMs might be very relevant. In this paper, we investigate the use few-shot training with the very large GPT (Generative Pre-trained Transformer) Codex model, and find evidence suggesting that one can significantly surpass state-of-the-art models for code-summarization, leveraging project-specific training.

Similar Work