Calibrate to Discriminate: Improve In-Context Learning with Label-Free Comparative Inference

Documenti analoghi

• Interpretable Discriminative Text Representations via Agreement and Label Disentanglement
  di: Wang, Tong, et al.
  Pubblicazione: (2026)
• Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference
  di: Zhou, Xuwen, et al.
  Pubblicazione: (2026)
• UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
  di: Zhou, Lang, et al.
  Pubblicazione: (2026)
• LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
  di: Gu, Zhuohan, et al.
  Pubblicazione: (2024)
• Label Smoothing Improves Gradient Ascent in LLM Unlearning
  di: Pang, Zirui, et al.
  Pubblicazione: (2025)