How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers

Documenti analoghi

• Annotating the Chain-of-Thought: A Behavior-Labeled Dataset for AI Safety
  di: Menke, Antonio-Gabriel Chacón, et al.
  Pubblicazione: (2025)
• DeepSeek reshaping healthcare in China's tertiary hospitals
  di: Chen, Jishizhan, et al.
  Pubblicazione: (2025)
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  di: DeepSeek-AI, et al.
  Pubblicazione: (2025)
• Bridging Technology and Humanities: Evaluating the Impact of Large Language Models on Social Sciences Research with DeepSeek-R1
  di: Gu, Peiran, et al.
  Pubblicazione: (2025)
• Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts
  di: Zhang, Wenjing, et al.
  Pubblicazione: (2025)