Demonstration Augmentation for Zero-shot In-context Learning

Documenti analoghi

• Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models
  di: Xiang, Yang, et al.
  Pubblicazione: (2025)
• Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries
  di: Tian, Zhenxu, et al.
  Pubblicazione: (2026)
• Revisiting Long-context Modeling from Context Denoising Perspective
  di: Tang, Zecheng, et al.
  Pubblicazione: (2025)
• Anti-LM Decoding for Zero-shot In-context Machine Translation
  di: Sia, Suzanna, et al.
  Pubblicazione: (2023)
• When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning
  di: Xiang, Yang, et al.
  Pubblicazione: (2026)