Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification

Documenti analoghi

• Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation
  di: Cegin, Jan, et al.
  Pubblicazione: (2024)
• RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets
  di: Cegin, Jan, et al.
  Pubblicazione: (2025)
• Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation
  di: Pecher, Branislav, et al.
  Pubblicazione: (2024)
• Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
  di: Pecher, Branislav, et al.
  Pubblicazione: (2026)
• Automatic Combination of Sample Selection Strategies for Few-Shot Learning
  di: Pecher, Branislav, et al.
  Pubblicazione: (2024)