Risk Assessment for LLMs
Research on methods for assessing, quantifying, and mitigating risks posed by large language models across various domains and applications
Risk Assessment for LLMs
Research on Large Language Models in Risk Assessment for LLMs
AI Diplomacy: Hidden Biases in LLMs
Benchmarking diplomatic preferences in major foundation models
The Illusion of Safety: When LLMs Judge LLMs
Revealing critical flaws in using LLMs as safety evaluators
The Python Preference Problem in AI
Uncovering LLMs' Biases in Programming Language Selection
The Self-Replication Threat Is Real
Multiple existing AI systems can already self-replicate without human intervention
Smarter Safety Alignment for LLMs
Using entropy to improve multi-criteria safety evaluations
Smart Risk Management for Modern Logistics
How LLMs Revolutionize Logistics Hub Network Deployment
Leveraging Product Recalls for Safer Design
Building RECALL-MM: A multimodal dataset for AI-powered risk analysis
