https://github.com/crhf/openai-rft-examples
Input-output examples highlighting the importance of fine-tuning LLMs for bug fixing tasks.
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (3.2%) to scientific vocabulary
Repository
Input-output examples highlighting the importance of fine-tuning LLMs for bug fixing tasks.
Basic Info
- Host: GitHub
- Owner: crhf
- Default Branch: main
- Size: 42 KB
Statistics
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Introduction
This repo contains two input-output examples of an LLM (Claude 3.5 Sonnet). The examples illustrate where the LLM falls short in producing bug fixes compared to human experts. Key takeaways from the examples are:
LLMs may fail to make reasonable generalizations from the issue, resulting in incomplete fixes.
LLMs may fail to follow project-specific conventions, leading to incorrect bug fixes.
The examples highlight the importance of fine-tuning LLMs for bug fixing tasks to improve their real-world usefulness and trustworthiness.
Owner
- Name: Haifeng Ruan
- Login: crhf
- Kind: user
- Company: @nus-se
- Repositories: 1
- Profile: https://github.com/crhf