Skip to content
#

paraphrase-type-generation

Star

Here is 1 public repository matching this topic...

cluebbers / dpo-rlhf-paraphrase-types

Star 0

End-to-end DPO fine-tuning pipeline for paraphrase-type generation (M.Sc. thesis, arXiv:2506.02018). DPO on 1,040 human-ranked pairs raised type accuracy +3 pp and human preference +7 pp over SFT baseline. Llama-3.1-8B + BART-large. Models on HuggingFace.

reinforcement-learning deep-learning transformers alignment arxiv paraphrase-generation human-feedback direct-preference-optimization paraphrase-type-generation
  • Updated Jun 4, 2025
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the paraphrase-type-generation topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the paraphrase-type-generation topic, visit your repo's landing page and select "manage topics."

Learn more