Evaluating Persistent Calibration under Evolving Model Knowledge
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-30
Updated: 2026-09-30
Comments: Code: https://github.com/victorwang37/persistent-calibration
Code: https://github.com/victorwang37/persistent-calibration
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
- Language Models (Mostly) Know What They Know
- Fast and Accurate Probing of In-Training LLMs' Downstream Performances
- Decoupled Weight Decay Regularization
- Large Language Model Agent: A Survey on Methodology, Applications and Challenges
- Measuring Calibration in Deep Learning
- Olmo 3
- Can LLMs Introspect? A Reality Check
- From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
- Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives
- TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
- Measuring short-form factuality in large language models
- The Truthfulness Spectrum Hypothesis
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks