RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets

Documenti analoghi

• Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
  di: Cegin, Jan, 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)
• Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation
  di: Cegin, Jan, et al.
  Pubblicazione: (2024)
• Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation
  di: Pecher, Branislav, et al.
  Pubblicazione: (2024)
• A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages
  di: Anikina, Tatiana, et al.
  Pubblicazione: (2025)