Introduces a margin-adaptive confidence ranking method that learns an estimator from simulated diversity and derives margin-dependent generalization bounds for use in fixed-sequence testing of LLM-human agreement.
Proceedings of the 26th Annual International Conference on Machine Learning , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The survey unifies extensions of PAC-Bayesian theory to data-dependent sets, geometric and topological complexity measures of optimization trajectories, and stability replacements for information terms into one template inequality with comparative evaluation.
citing papers explorer
-
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
Introduces a margin-adaptive confidence ranking method that learns an estimator from simulated diversity and derives margin-dependent generalization bounds for use in fixed-sequence testing of LLM-human agreement.
-
A Survey on Data-Dependent Worst-Case Generalization Bounds
The survey unifies extensions of PAC-Bayesian theory to data-dependent sets, geometric and topological complexity measures of optimization trajectories, and stability replacements for information terms into one template inequality with comparative evaluation.