When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training

arXiv:2606.14629 · cs.CR, cs.AI · Submitted 2026-06-12 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-06-12

Updated: 2026-09-25

Comments: 15 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 145× in this paper · explained in 2 episodes
• Accuracy — 41× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Calibration — 4× in this paper · explained in 7 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Anisotropy — 1× in this paper · explained in 3 episodes
• Asymmetric Acceptance Gating — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Reinforced Self-Training (ReST) for Language Modeling
• Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent
• Iterative Reasoning Preference Optimization

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs