Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs

Documenti analoghi

• EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
  di: Mohammadi, Hadi, et al.
  Pubblicazione: (2025)
• Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
  di: Mohammadi, Hadi, et al.
  Pubblicazione: (2025)
• Explainability in Practice: A Survey of Explainable NLP Across Various Domains
  di: Mohammadi, Hadi, et al.
  Pubblicazione: (2025)
• Explainability-Based Token Replacement on LLM-Generated Text
  di: Mohammadi, Hadi, et al.
  Pubblicazione: (2025)
• Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
  di: Jia, Jinghan, et al.
  Pubblicazione: (2026)