Aligning LLMs by Predicting Preferences from User Writing Samples

Documenti analoghi

• PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories
  di: Aroca-Ouellette, Stephane, et al.
  Pubblicazione: (2024)
• Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards
  di: Metcalf, Katherine, et al.
  Pubblicazione: (2024)
• Theoretical Limits of Language Model Alignment
  di: Paes, Lucas Monteiro, et al.
  Pubblicazione: (2026)
• Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
  di: Wang, Yinong Oliver, et al.
  Pubblicazione: (2025)
• Bias after Prompting: Persistent Discrimination in Large Language Models
  di: Sivakumar, Nivedha, et al.
  Pubblicazione: (2025)