Preprocessed datasets for training and evaluating DDRO generative retrieval models on MS MARCO and Natural Questions.
Kidist Amde Mekonnen
kiyam
AI & ML interests
AI (Generative models, Computer vision, NLP) ,XAI
Recent Activity
updated a collection about 3 hours ago
Embed2DocID updated a collection about 3 hours ago
Embed2DocID published a model 28 days ago
kiyam/lost-in-decoding-pagOrganizations
Preprocessed datasets for training and evaluating DDRO generative retrieval models on MS MARCO and Natural Questions.
Step-2 SFT reference policies (π_ref) used to initialize DDRO (MS MARCO / NQ; PQ and Title+URL DocIDs); use these for fair comparisons/ablations.
Step-3 DDRO optimized checkpoints (final policy) + accompanying datasets/artifacts (docIDs, pseudo-queries, testsets) to reproduce the paper.