提升大模型推理的可信度，让结果更可解释、更忠实、更可靠。
ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
- 引入结构化标签追踪与高层规划，增强推理过程可读性。
- 显式披露决策依据，跨段落引用保持一致性，提升忠实度。
- 加入自我评估机制，输出答案置信度，增强可靠性判断能力。
近期长链思维（CoT）推理的发展主要关注答案准确性和生成效率，却忽视了可信度的关键维度。我们认为，可用的推理系统必须具备可解释性、忠实性和可靠性。为此，我们提出ReFIne训练框架，结合监督微调与GRPO方法，使模型：(i) 通过生成带标签的结构化推理轨迹和高层规划，提升可解释性；(ii) 显式揭示每一步决策所依赖的关键信息，并保持跨段落一致引用，增强忠实性；(iii) 提供对推导过程合理性和最终答案置信度的自我评估。我们在Qwen3系列模型（1.7B/4B/8B）上应用ReFIne，在不同难度的数学基准上进行评估。实验表明，ReFIne模型在推理轨迹清晰度和结构化程度上提升44.0%，决策过程暴露更忠实，提升18.8%，且提供有信息量的置信度估计，可靠性提升42.4%。结果表明，推理模型应不仅追求准确性，还需优化可信度多维指标。代码已开源：https://github.com/Trustworthy-ML-Lab/Training_Trustworthy_LRM_with_Refine。
原文摘要 · Abstract (English)
Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects critical to trustworthiness. We argue that usable reasoning systems must be trustworthy, characterized by three properties: interpretability, faithfulness, and reliability. To this end, we propose ReFIne, a new training framework that integrates supervised fine-tuning with GRPO to encourage models to: (i) improve interpretability by producing structured, tag-based traces with high-level planning that are easier for humans to follow; (ii) enhance faithfulness by explicitly disclosing the decisive information guiding each solution, with consistent cross-section references; and (iii) promote reliability by providing self-assessments of both the derivation's soundness and the confidence of the final answer. We apply ReFIne to the Qwen3 models at multiple scales (1.7B/4B/8B) and evaluate across mathematical benchmarks of varying difficulty. Our experimental results show that ReFIne models generate clearer and better-structured reasoning traces (interpretability +44.0%), more faithfully expose their underlying decision process (faithfulness +18.8%), and offer informative confidence estimates (reliability +42.4%). These findings highlight an overlooked but important direction: reasoning models should be optimized not only for accuracy, but also for broader dimensions of trustworthiness. Our code is available at: https://github.com/Trustworthy-ML-Lab/Training_Trustworthy_LRM_with_Refine
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。