Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation

Documenti analoghi

• TinyHelen's First Curriculum: Training and Evaluating Tiny Language Models in a Simpler Language Environment
  di: Yang, Ke, et al.
  Pubblicazione: (2024)
• Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement
  di: Sun, Chenkai, et al.
  Pubblicazione: (2024)
• An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
  di: Hao, Yuren, et al.
  Pubblicazione: (2025)
• User Simulation for Evaluating Information Access Systems
  di: Balog, Krisztian, et al.
  Pubblicazione: (2023)
• The Indispensable Role of User Simulation in the Pursuit of AGI
  di: Balog, Krisztian, et al.
  Pubblicazione: (2025)