Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
arXiv preprint arXiv:2205.07276 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
CLIPer uses classifier guidance during inference to personalize LLM generations across single and multi-dimensional user preferences without extensive fine-tuning.
citing papers explorer
-
Multi-Objective Exploration and Preference Optimization via Mutual Information
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
-
CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization
CLIPer uses classifier guidance during inference to personalize LLM generations across single and multi-dimensional user preferences without extensive fine-tuning.