#inference-time-safety News & Analysis

2 articles tagged with #inference-time-safety. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBullisharXiv – CS AI · Mar 67/10

🧠

Design Behaviour Codes (DBCs): A Taxonomy-Driven Layered Governance Benchmark for Large Language Models

Researchers introduce the Dynamic Behavioral Constraint (DBC) benchmark, a new governance framework for large language models that reduces AI risk exposure by 36.8% through structured behavioral controls applied at inference time. The system achieves high EU AI Act compliance scores and represents a model-agnostic approach to AI safety that can be audited and mapped to different jurisdictions.

AIBullisharXiv – CS AI · Jun 116/10

🧠

To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending

Researchers introduce BlendIn, an inference-time alignment framework for large language models that uses probabilistic model blending instead of binary intervention decisions. The method dynamically weights guidance from multiple models based on reliability, achieving up to 50% performance improvement by reducing ineffective interventions that typically degrade output quality.