AINeutralarXiv – CS AI · Jun 17/10
🧠Researchers demonstrate that large language models trained to produce dishonest outputs develop clear, detectable internal representations of deception across multiple architectures. Using linear probes on transformer models, the study achieves near-perfect accuracy in identifying synthetic dishonesty, with implications for AI safety monitoring and the feasibility of detecting deceptive alignment in advanced language models.
🧠 Llama
AINeutralarXiv – CS AI · May 287/10
🧠Researchers systematically tested linear probes used to detect deception in large language models, finding they achieve near-perfect accuracy on clean data but fail dramatically under distributional shifts. The study reveals deception is encoded through distributed multi-dimensional features rather than a single direction, and probe robustness can be recovered through style augmentation, indicating failures stem from narrow training distributions rather than fundamental architectural limitations.
AIBullisharXiv – CS AI · May 127/10
🧠Researchers propose using 'persona coordinates'—low-dimensional subspaces derived from contrasting harmful and harmless model behaviors—to improve the generalization of linear probes that monitor language models for deception and harmful outputs. Testing across 10 datasets shows that probes trained on persona-derived directions significantly outperform those trained on raw model activations, addressing a critical gap in AI safety monitoring.
AINeutralarXiv – CS AI · Mar 47/102
🧠Researchers developed linear probes that can predict whether large language models will answer questions correctly by analyzing neural activations before any answer is generated. The method works across different model sizes and generalizes to out-of-distribution datasets, though it struggles with mathematical reasoning tasks.
AINeutralarXiv – CS AI · Jun 196/10
🧠Researchers demonstrate that universal linear probes for detecting AI deception are fundamentally limited, achieving only modest performance improvements. The study reveals deception detection requires type-specific probes tailored to particular threat models rather than single universal detectors, with performance varying significantly based on instruction pair design.
AINeutralarXiv – CS AI · Mar 96/10
🧠Researchers analyzed Vision-Language Models (VLMs) used in automated driving to understand why they fail on simple visual tasks. They identified two failure modes: perceptual failure where visual information isn't encoded, and cognitive failure where information is present but not properly aligned with language semantics.
AINeutralarXiv – CS AI · Mar 37/108
🧠New research reveals that large language models often determine their final answers before generating chain-of-thought reasoning, challenging the assumption that CoT reflects the model's actual decision process. Linear probes can predict model answers with 0.9 AUC accuracy before CoT generation, and steering these activations can flip answers in over 50% of cases.
