Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

Documenti analoghi

• Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
  di: Zhou, Zhanhui, et al.
  Pubblicazione: (2023)
• Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
  di: Zhou, Zhanhui, et al.
  Pubblicazione: (2024)
• MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues
  di: Bai, Ge, et al.
  Pubblicazione: (2024)
• ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
  di: Wu, Yanan, et al.
  Pubblicazione: (2024)
• 2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision
  di: Li, Shilong, et al.
  Pubblicazione: (2024)