Rethinking Epistemic Uncertainty in Node Classification through Information GrowthResearchOct 5, 2026
Sentence-Level Context Sensitivity as a Training-Free Detector of Unsupported Content, Evaluated Against Trained VerifiersResearchOct 5, 2026
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task PerformanceResearchOct 5, 2026
When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model BehaviorResearchOct 5, 2026
Mapping and Advancing the Scalability-Accuracy Frontier of Nonlinear Causal DiscoveryResearchOct 5, 2026
Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable TokensResearchOct 5, 2026