Simple synthetic data reduces sycophancy in large language models

Documenti analoghi

• Symbol tuning improves in-context learning in language models
  di: Wei, Jerry, et al.
  Pubblicazione: (2023)
• Long-form factuality in large language models
  di: Wei, Jerry, et al.
  Pubblicazione: (2024)
• Zero-shot generation of synthetic neurosurgical data with large language models
  di: Barr, Austin A., et al.
  Pubblicazione: (2025)
• Ask don't tell: Reducing sycophancy in large language models
  di: Dubois, Magda, et al.
  Pubblicazione: (2026)
• Large Language Models as Optimizers
  di: Yang, Chengrun, et al.
  Pubblicazione: (2023)