A Function-Level Vulnerability Score Measures Flag Rate More Than the Model: Protocol Effects on Paired Benchmarks

arXiv:2609.32890 · cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Benchmark — 54× in this paper · explained in 2 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Linear probe — 8× in this paper · explained in 2 episodes
• GRPO — 5× in this paper · explained in 6 episodes
• In International Conference on Learning Representations — 3× in this paper
• RAG — 3× in this paper · explained in 3 episodes
• ACM International Conference on Software Engineering — 2× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Abliteration — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Quantization — 1× in this paper · explained in 12 episodes

Sources

• Understanding intermediate layers using linear classifier probes
• The Internal State of an LLM Knows When It's Lying
• Probing Classifiers: Promises, Shortcomings, and Advances
• Discovering Latent Knowledge in Language Models Without Supervision
• Deep Learning based Vulnerability Detection: Are We There Yet?
• Data Quality for Software Vulnerability Datasets
• Vulnerability Detection with Code Language Models: How Far Are We?
• Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG
• Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
• Designing and Interpreting Probes with Control Tasks
• Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
• "Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
• VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization
• From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
• The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
• ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software
• LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
• Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?
• Top Score on the Wrong Exam: On Benchmarking in Machine Learning for Vulnerability Detection

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