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.
Reward consistency: Improv- ing multi-objective alignment from a data-centric perspective
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2roles
method 1polarities
use method 1representative citing papers
MORA breaks the safety-helpfulness ceiling in LLMs by pre-sampling single-reward prompts and rewriting them to incorporate multi-dimensional intents, delivering 5-12.4% gains in sequential alignment and 4.6% overall improvement in simultaneous alignment.
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.
-
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
MORA breaks the safety-helpfulness ceiling in LLMs by pre-sampling single-reward prompts and rewriting them to incorporate multi-dimensional intents, delivering 5-12.4% gains in sequential alignment and 4.6% overall improvement in simultaneous alignment.