https://github.com/crhf/openai-rft-examples

Input-output examples highlighting the importance of fine-tuning LLMs for bug fixing tasks.

https://github.com/crhf/openai-rft-examples

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
Last synced: 10 months ago · JSON representation

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
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme

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:

  1. LLMs may fail to make reasonable generalizations from the issue, resulting in incomplete fixes.

  2. 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

GitHub Events

Total
Last Year