Contrastive-Learning

• Contriever

  Unsupervised dense retrieval model trained with contrastive learning on unlabeled text; no labeled query-passage pairs required.

• In-Batch Negatives

  Training technique where other (query, passage) pairs within the same mini-batch serve as negatives; free negative supervision that scales with batch size.

• SimCSE

  Simple Contrastive Sentence Embeddings; learns high-quality sentence representations via dropout-based augmentation (unsupervised) or NLI entailment pairs (supervised).