SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
–Neural Information Processing Systems
Ensuring the safety of large language model (LLM) applications is essential for developing trustworthy artificial intelligence.
Neural Information Processing Systems
Nov-20-2025, 05:26:25 GMT
- Country:
- Asia > China (0.04)
- North America > United States
- California > Orange County > Mission Viejo (0.04)
- Genre:
- Research Report (0.46)
- Industry:
- Health & Medicine (0.68)
- Information Technology > Security & Privacy (0.94)
- Law (0.93)
- Technology: