CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning

Documenti analoghi

• AdaBoN: Adaptive Best-of-N Alignment
  di: Raman, Vinod, et al.
  Pubblicazione: (2025)
• RoBoN: Routed Online Best-of-n for Test-Time Scaling with Multiple LLMs
  di: Geuter, Jonathan, et al.
  Pubblicazione: (2025)
• TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
  di: Qiu, Jiahao, et al.
  Pubblicazione: (2024)
• Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling
  di: Rho, Hyung Gyu, et al.
  Pubblicazione: (2025)
• Defining and Evaluating Physical Safety for Large Language Models
  di: Tang, Yung-Chen, et al.
  Pubblicazione: (2024)