Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging

Documenti analoghi

• SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
  di: Hu, Tiancheng, et al.
  Pubblicazione: (2025)
• MAGIC: Achieving Superior Model Merging via Magnitude Calibration
  di: Li, Yayuan, et al.
  Pubblicazione: (2025)
• Pareto Multi-Objective Alignment for Language Models
  di: He, Qiang, et al.
  Pubblicazione: (2025)
• Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation
  di: Frohmann, Markus, et al.
  Pubblicazione: (2024)
• Merge to Mix: Mixing Datasets via Model Merging
  di: Tao, Zhixu Silvia, et al.
  Pubblicazione: (2025)