類似資料

• Soft Best-of-n Sampling for Model Alignment
  著者:: Verdun, Claudio Mayrink, 等
  出版事項: (2025)
• Inference-Time Reward Hacking in Large Language Models
  著者:: Khalaf, Hadi, 等
  出版事項: (2025)
• Multi-Group Proportional Representation in Retrieval
  著者:: Oesterling, Alex, 等
  出版事項: (2024)
• Algorithmic Arbitrariness in Content Moderation
  著者:: Gomez, Juan Felipe, 等
  出版事項: (2024)
• Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
  著者:: Bhalla, Usha, 等
  出版事項: (2025)