Reinforcement-Calibration-SimCSE
PublicReinforcement Calibration SimCSE, combining contrastive learning, artificial potential fields, perceptual loss, and RLHF to achieve improved Semantic Textual Similarity (STS) embeddings. PyTorch-based implementations of PerceptualBERT and ForceBasedInfoNCE, along with fine-tuning capabilities via RLHF and evaluation using SentEval.
artificial-potential-fieldscontrastive-learningnlprlhfself-supervised-learningsemantic-textual-similaritysentence-embeddingssentevalsimcse
Creat：2024-12-24T22:24:22
Update：2025-01-16T09:30:58
11
Stars
0
Stars Increase