Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning

Documenti analoghi

• Language Evolution with Deep Learning
  di: Rita, Mathieu, et al.
  Pubblicazione: (2024)
• Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach
  di: Poli, Maxime, et al.
  Pubblicazione: (2024)
• fastabx: A library for efficient computation of ABX discriminability
  di: Poli, Maxime, et al.
  Pubblicazione: (2025)
• Reinforcement Learning Amplifies Emergent Misalignment from Harmless Rewards
  di: Jørgenvåg, Magnus, et al.
  Pubblicazione: (2026)
• Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning
  di: Ahmadi, Arash, et al.
  Pubblicazione: (2026)