ConvRecStudio generates roughly 38K synthetic multi-turn recommendation dialogs across three domains from historical interactions, and a cross-attention transformer fusing history with dialog beats dialog-only and history-only baselines on those dialogs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions
ConvRecStudio generates roughly 38K synthetic multi-turn recommendation dialogs across three domains from historical interactions, and a cross-attention transformer fusing history with dialog beats dialog-only and history-only baselines on those dialogs.