Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation

Documenti analoghi

• On the Step Length Confounding in LLM Reasoning Data Selection
  di: Wang, Bing, et al.
  Pubblicazione: (2026)
• Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation
  di: Liu, Kaiyuan, et al.
  Pubblicazione: (2025)
• Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
  di: Wang, Bing, et al.
  Pubblicazione: (2026)
• Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
  di: Yan, Shaotian, et al.
  Pubblicazione: (2026)
• SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning
  di: Xin, Yue, et al.
  Pubblicazione: (2025)