RAGR builds mixed item-review sequences for generative recommendation and uses DPO alignment to favor item tokens, reporting gains over prior GR baselines on three datasets.
Exploring the limits of transfer learning with a unified text-to-text transformer,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RAGR: Review-Augmented Generative Recommendation
RAGR builds mixed item-review sequences for generative recommendation and uses DPO alignment to favor item tokens, reporting gains over prior GR baselines on three datasets.