CausalCoT：用上下文隔离提升思维链的因果可信度
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
这篇论文指出了 CoT 一个老毛病：推理步骤可能是事后编的。CausalCoT 把问题拆成依赖图逐个隔离求解，因果敏感度平均涨了 12 个百分点。
思维链提示给出的推理步骤未必真正决定最终答案。CausalCoT 把问题拆解成有向无环图，每个子问题只在包含直接因果父节点的隔离上下文中评估，阻断注意力对无关内容的泄漏。在多个推理基准上，其因果敏感度平均提升 12 个百分点，最高提升 21 个百分点，预测性能与最强基线持平。依赖图结构还支持测试时干预，局部修正可沿图向下传播。
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no guarantee these steps causally drive the final answer. In standard autoregressive generation, dense attention allows each reasoning step to attend to the full context, enabling the model to derive answers through direct lookup while generating plausible-sounding but post-hoc justifications. We introduce CausalCoT, an inference framework that enforces causal transparency by decomposing problems into a directed acyclic graph of atomic sub-questions, evaluating each node in an isolated context containing only its direct causal parents. This Markovian structure removes attention pathways to non-parent content, making downstream predictions sensitive to local reasoning rather than global context leakage. Across a diverse suite of reasoning benchmarks, CausalCoT preserves competitive predictive performance while improving explanation faithfulness, increasing causal sensitivity of intermediate reasoning steps by an average of 12 and up to 21 percentage points over the strongest baseline. The structured dependency graph additionally enables test-time interventions in which local corrections propagate predictably through downstream reasoning.
