Auditing System-1 Models on Biosecurity-Relevant Benchmarks: Calibration, Selective Prediction, and Permutation Instability in a Non-Generative Model

arXiv:2609.30454 · cs.LG · Submitted 2026-09-24 · Read on arXiv

cs.LG

Submitted: 2026-09-24

Updated: 2026-09-24

Code: https://github.com/Georgakopoulos-Soares-lab/biosafety_knowledge_jev

Terminology

• Accuracy — 42× in this paper · explained in 1 episode
• Benchmark — 15× in this paper · explained in 2 episodes
• Calibration — 15× in this paper · explained in 7 episodes
• AUROC — 13× in this paper · explained in 2 episodes
• Generative Model — 8× in this paper · explained in 2 episodes
• Abstention — 3× in this paper · explained in 1 episode
• International Conference on Learning Representations — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Weapons of Mass Destruction Proxy — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Deferral — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Speculative Decoding — 1× in this paper · explained in 2 episodes

Sources

• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
• LAB-Bench: Measuring Capabilities of Language Models for Biology Research
• Changing Answer Order Can Decrease MMLU Accuracy
• ShieldGemma: Generative AI Content Moderation Based on Gemma
• Will releasing the weights of future large language models grant widespread access to pandemic agents?

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks