CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
CARD personalizes LLMs with cluster LoRA adapters and decoding-time preference vectors, beating LaMP and LongLaMP baselines.
1 stories, newest first · one card per story
CARD personalizes LLMs with cluster LoRA adapters and decoding-time preference vectors, beating LaMP and LongLaMP baselines.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views