From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought

Documenti analoghi

• Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution
  di: Tan, Wentao, et al.
  Pubblicazione: (2024)
• Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
  di: Xu, Rongwu, et al.
  Pubblicazione: (2024)
• Rationale-Aware Answer Verification by Pairwise Self-Evaluation
  di: Kawabata, Akira, et al.
  Pubblicazione: (2024)
• xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
  di: Chen, Ding, et al.
  Pubblicazione: (2025)
• Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation
  di: Xie, Hongyan, et al.
  Pubblicazione: (2025)