Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs

Documenti analoghi

• Debating with More Persuasive LLMs Leads to More Truthful Answers
  di: Khan, Akbir, et al.
  Pubblicazione: (2024)
• TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation
  di: Cook, Jonathan, et al.
  Pubblicazione: (2024)
• Investigating Non-Transitivity in LLM-as-a-Judge
  di: Xu, Yi, et al.
  Pubblicazione: (2025)
• Scaling Opponent Shaping to High Dimensional Games
  di: Khan, Akbir, et al.
  Pubblicazione: (2023)
• High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
  di: Franzmeyer, Tim, et al.
  Pubblicazione: (2025)