Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
0
This work introduces rubric-based preference reasoning, which uses automated rubrics to guide the model toward producing explicit preference states, and proposes a preference-conditioned optimization to align response generation with dual objectives: user preference satisfaction and situation consistency.
SiPeR reveals how integrating scene dynamics with Bayesian inference can dramatically enhance the relevance of conversational recommendations in real-world contexts.
