PFID: Privacy First Inference Delegation Framework for LLMs

Documenti analoghi

• Leveraging Biases in Large Language Models: "bias-kNN'' for Effective Few-Shot Learning
  di: Zhang, Yong, et al.
  Pubblicazione: (2024)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
  di: Li, Ming, et al.
  Pubblicazione: (2023)
• QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
  di: Ouyang, Sheng, et al.
  Pubblicazione: (2024)
• Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
  di: Li, Ming, et al.
  Pubblicazione: (2024)
• GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression
  di: Liu, Kainan, et al.
  Pubblicazione: (2024)