PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models

Documenti analoghi

• PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning
  di: Zhao, Xueliang, et al.
  Pubblicazione: (2025)
• Scaling Reasoning without Attention
  di: Zhao, Xueliang, et al.
  Pubblicazione: (2025)
• DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
  di: Zhao, Xueliang, et al.
  Pubblicazione: (2025)
• CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models
  di: Chen, Zhuofan, et al.
  Pubblicazione: (2025)
• Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
  di: Cherian, Anoop, et al.
  Pubblicazione: (2024)