Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization

Documenti analoghi

• PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery
  di: He, Bowei, et al.
  Pubblicazione: (2025)
• Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak
  di: Huang, Zixuan, et al.
  Pubblicazione: (2025)
• Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
  di: Liu, Shuqi, et al.
  Pubblicazione: (2025)
• 1bit-Merging: Dynamic Quantized Merging for Large Language Models
  di: Liu, Shuqi, et al.
  Pubblicazione: (2025)
• Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models
  di: Liu, Shuqi, et al.
  Pubblicazione: (2025)