这是篇讲怎么把大模型因果推理能力蒸馏到小模型的新论文，CausalOPD专治“答案对但推理过程错”，三个领域里错误率从15.7%砍到4.4%，小模型还赢过了大牌模型。
CausalOPD是一种课程式在线过程蒸馏框架，让教师模型先基于因果规则生成轨迹，再由学生模型在线生成并定位首个违反约束的错误步骤。框架通过短视距强化学习修复局部错误，并按证据级、机制级、结论级的因果阶段推进训练。在临床诊断、法律判断和工业故障诊断三个领域，CausalOPD将路径正确率平均提升23.4个百分点，并将“答案对但推理错”的比例从15.7%降至4.4%。基于该方法的8B学生模型在路径正确率上超过两个商业参考模型。
CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain Reasoning
Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in which early errors propagate and correct conclusions can mask invalid reasoning. Although large language models perform well on such tasks, privacy, latency, and controllability motivate distillation into locally deployable models. Standard trajectory imitation does not correct process errors on the student's own rollout distribution. We propose CausalOPD, a curriculum online process distillation framework. A knowledge-augmented teacher first provides trajectories grounded in domain-specific causal rules, entity relations, and structural constraints. The student then generates on-policy trajectories, and the teacher identifies the first wrong step, defined as the earliest transition that verifiably violates available constraints. Starting from the verified prefix, short-horizon reinforcement learning repairs this localized failure. A causal-stage curriculum advances from evidence-level to mechanism-level and conclusion-level errors, following their propagation order. Across three domains, CausalOPD improves average path correctness by 23.4 percentage points over sequence-level online process distillation and reduces the right-label-wrong-reasoning rate from 15.7% to 4.4%. The domain-specific 8B students also surpass both evaluated proprietary references in path correctness across all domains.