https://github.com/cluebbers/dpo-rlhf-paraphrase-types

Enhancing paraphrase-type generation using Direct Preference Optimization (DPO) and Reinforcement Learning from Human Feedback (RLHF), with large-scale HPC support. This project aligns model outputs to human-ranked data for robust, safety-focused NLP.

alignment deep-learning direct-preference-optimization human-feedback paraphrase-generation paraphrase-type-generation reinforcement-learning transformers

Last synced: 02 Jul 2025