CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards

Documenti analoghi

• CEC-Zero: Chinese Error Correction Solution Based on LLM
  di: Zhang, Sophie, et al.
  Pubblicazione: (2025)
• Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
  di: He, Yinghui, et al.
  Pubblicazione: (2026)
• A Training-free LLM-based Approach to General Chinese Character Error Correction
  di: Zhou, Houquan, et al.
  Pubblicazione: (2025)
• Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards
  di: Jia, Ruipeng, et al.
  Pubblicazione: (2025)
• Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
  di: Liu, Runheng, et al.
  Pubblicazione: (2026)