Exploring Explanations Improves the Robustness of In-Context Learning

Documenti analoghi

• Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding
  di: Honda, Ukyo, et al.
  Pubblicazione: (2024)
• Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts
  di: Jinnai, Yuu, et al.
  Pubblicazione: (2024)
• Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
  di: Kajitsuka, Tokio, et al.
  Pubblicazione: (2026)
• A Single Linear Layer Yields Task-Adapted Low-Rank Matrices
  di: Kim, Hwichan, et al.
  Pubblicazione: (2024)
• Exploring the Robustness of In-Context Learning with Noisy Labels
  di: Cheng, Chen, et al.
  Pubblicazione: (2024)