This work introduces the Epistemic Honesty Quotient (EHQ), which reports three observable sub-scores across two operational axes (epistemic restraint and substantive-answer calibration), and constructs EHQ-3000, a 3,000-question benchmark spanning Fabricated Entity, Post-Cutoff Event, Hyper-Niche True, and Context-Cond...
RQEval is proposed, a unified multi-dimensional framework for measuring LLM reasoning quality from a behavioral perspective that operationalizes six theoretically grounded dimensions rooted in cognitive science and introduces deployment-aware aggregation, enabling context-specific model selection beyond accuracy-based...
Ali Şenol, Garima Agrawal, Huan Liu· Big Data and Cognitive Compu...· 2 citations
This work introduces MUGEN, to its knowledge the first framework for generating unlearnable graph examples that jointly protect all enabled tasks, and devise a Task-Aligned Separability Objective (TASO), which leverages task prediction and classwise separability to strengthen unlearnability and its transfer across GNN...
