Accuracy Is Not Value: Choosing Weak Supervisors by What the Student Inherits
cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
- Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels
- Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts
- Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning
- Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression
- On the Emergence of Weak-to-Strong Generalization: A Bias-Variance Perspective
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis