CARD uses style-based user clustering and implicit preference contrasts to enable efficient personalized text generation via lightweight decoding adjustments on frozen LLMs.
InProceedings of the Open Source Information Retrieval Workshop, pages 116–123
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
CARD uses style-based user clustering and implicit preference contrasts to enable efficient personalized text generation via lightweight decoding adjustments on frozen LLMs.