CodeT5+ 770m for classifying smell documentation (multi-label)

This model classifies smell documentation as 'fragmented', 'tangled', 'excessive', 'bloated' or 'lazy'.

• Developed by: Fabian C. Peña, Steffen Herbold
• Finetuned from: Salesforce/codet5p-770m
• Replication kit: https://github.com/aieng-lab/senlp-benchmark
• Language: English
• License: MIT

Citation

@misc{pena2025benchmark,
  author    = {Fabian Peña and Steffen Herbold},
  title     = {Evaluating Large Language Models on Non-Code Software Engineering Tasks},
  year      = {2025}
}