Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation

Documenti analoghi

• Kaleidoscopic Teaming in Multi Agent Simulations
  di: Mehrabi, Ninareh, et al.
  Pubblicazione: (2025)
• K-Edit: Language Model Editing with Contextual Knowledge Awareness
  di: Markowitz, Elan, et al.
  Pubblicazione: (2025)
• Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification
  di: Meng, Tao, et al.
  Pubblicazione: (2024)
• Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
  di: Markowitz, Elan, et al.
  Pubblicazione: (2024)
• On the steerability of large language models toward data-driven personas
  di: Li, Junyi, et al.
  Pubblicazione: (2023)