PRISM
Emerging4papers using it
2025first seen
Papers using PRISM (4)
- CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of AdaptersSynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMsSynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward
Models in LLMsDrift: Decoding-time Personalized Alignments with Implicit User
Preferences