#safety-metrics News & Analysis

3 articles tagged with #safety-metrics. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AINeutralarXiv – CS AI · Jun 107/10

🧠

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

Researchers discovered that key-value cache quantization—a technique used to reduce LLM inference memory—silently degrades AI safety alignment without affecting standard performance metrics like perplexity. The study identifies the root cause as geometric vulnerability of safety features in low-dimensional activation subspaces and proposes Per-Channel Reduction (PCR), a diagnostic tool that achieves up to 97% alignment recovery without retraining.

🏢 Nvidia🏢 Perplexity

AINeutralarXiv – CS AI · Jun 236/10

🧠

Safety-Aware Evaluation of LLM-Generated Driver Intervention Messages through Multi-Task Risk Fusion

Researchers propose the Driver Safety-Aware Intervention Score (DSAIS), a domain-specific metric for evaluating LLM-generated driver safety messages across five dimensions including risk-urgency alignment and cognitive load. The framework integrates multi-task recognition outputs through risk fusion and achieves strong inter-rater reliability (ICC 0.798-0.840), demonstrating that compact local LLMs outperform API-based models for in-vehicle deployment.

AINeutralOpenAI News · Nov 126/103

🧠

GPT-5.1 Instant and GPT-5.1 Thinking System Card Addendum

OpenAI has released a system card addendum for GPT-5.1 Instant and GPT-5.1 Thinking models, providing updated safety metrics and evaluations. The addendum includes new assessments focused on mental health considerations and potential emotional reliance issues with the advanced AI systems.