Temporal Preference Optimization for Unsupervised Retrieval
Microsoft presents a preference-based training method that injects temporal awareness into unsupervised dense retrievers, helping them favor temporally aligned documents.
š arxiv.org/abs/2606.17664
šØš½āš» github.com/agwaBom/TPOUR
Unsupervised dense retrievers offer scalability by learning semantic similarity from unlabeled documents via contrastive learning, but they struggle to capture the temporal relevance, retrieving seman...
