Understanding and Mitigating Premature Confidence for Better LLM Reasoning

Documenti analoghi

• Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
  di: Gai, Jingchu, et al.
  Pubblicazione: (2025)
• Weight Ensembling Improves Reasoning in Language Models
  di: Dang, Xingyu, et al.
  Pubblicazione: (2025)
• Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
  di: Kim, Eungyeup, et al.
  Pubblicazione: (2023)
• Why is SAM Robust to Label Noise?
  di: Baek, Christina, et al.
  Pubblicazione: (2024)
• Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
  di: Ball, Sarah, et al.
  Pubblicazione: (2025)