technique
reward-induced maximum likelihood
techniqueactiveprovisional
reward-induced-maximum-likelihood-07e746b7·1 events·first seen 21d agoAliases: reward-induced maximum likelihood
Co-occurring entities
More like this (12)
Maximum Likelihood Estimationlikelihood approximationreward modelGradient-Guided Reward OptimizationLog Probability Bias AnalysisELBO variance minimizationEntropy-Regularized Reinforcement LearningBayesian Optimizationposterior predictive variance minimizationScaling Laws for Reward Model OveroptimizationInvariant Risk MinimizationKL-regularized RL
Recent events (1)
GraphReview: Scientific Paper Evaluation via LLM-Based Graph Message Passing
GraphReview proposes a graph-based LLM framework that models scientific paper evaluation as review-signal message passing over a semantic paper graph, capturing both intrinsic quality and relational context (synchronic and diachronic links). LLMs estimate node-level quality priors and generate edge-level comparative evidence via pairwise comparisons, while Personalized PageRank integrates signals for ranking, decision prediction, and review generation. The system uses reward-induced maximum likelihood objectives to train LLM backbones and achieves average improvements of 29.7% over the strongest baseline on decision and ranking metrics, including 23.7% accuracy gain and 57.6% Spearman's ρ gain.