Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution

Documenti analoghi

• Spectral Surgery: Training-Free Refinement of LoRA via Gradient-Guided Singular Value Reweighting
  di: Tian, Zailong, et al.
  Pubblicazione: (2026)
• Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement
  di: Lu, Junyu, et al.
  Pubblicazione: (2025)
• Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
  di: Xu, Yuanda, et al.
  Pubblicazione: (2026)
• Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs
  di: Xu, Chenjun, et al.
  Pubblicazione: (2025)
• Aligned Multi-View Scripts for Universal Chart-to-Code Generation
  di: Zhang, Zhihan, et al.
  Pubblicazione: (2026)