Reinforcement 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.
nlp semantic-textual-similarity sentence-embeddings self-supervised-learning senteval contrastive-learning simcse rlhf artificial-potential-fields
-
Updated
Dec 24, 2024 - Python