Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging

Documenti analoghi

• KLoB: a Benchmark for Assessing Knowledge Locating Methods in Language Models
  di: Ju, Yiming, et al.
  Pubblicazione: (2023)
• SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms
  di: Xing, Xingrun, et al.
  Pubblicazione: (2024)
• SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation
  di: Kapusuzoglu, Berkcan, et al.
  Pubblicazione: (2025)
• Correlation-Aware Select and Merge Attention for Efficient Fine-Tuning and Context Length Extension
  di: Wang, Ning, et al.
  Pubblicazione: (2024)
• Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
  di: Lai, Song, et al.
  Pubblicazione: (2025)