Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach
This paper introduces Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings, and introduces Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings.