Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration

Documenti analoghi

• The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
  di: Chen, Yanjun, et al.
  Pubblicazione: (2024)
• Don't Forget to Connect! Improving RAG with Graph-based Reranking
  di: Dong, Jialin, et al.
  Pubblicazione: (2024)
• As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
  di: Mao, Xin, et al.
  Pubblicazione: (2024)
• HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
  di: Tong, Xin, et al.
  Pubblicazione: (2025)
• sDPO: Don't Use Your Data All at Once
  di: Kim, Dahyun, et al.
  Pubblicazione: (2024)