Using Natural Language Explanations to Improve Robustness of In-context Learning

Documenti analoghi

• SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations
  di: Solano, Jesus, et al.
  Pubblicazione: (2023)
• TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
  di: He, Xuanli, et al.
  Pubblicazione: (2024)
• Atomic Inference for NLI with Generated Facts as Atoms
  di: Stacey, Joe, et al.
  Pubblicazione: (2023)
• The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
  di: Siegel, Noah Y., et al.
  Pubblicazione: (2024)
• Identifying Linear Relational Concepts in Large Language Models
  di: Chanin, David, et al.
  Pubblicazione: (2023)