这篇论文用辛普森悖论测试干预数据，发现模型因果方向取决于上下文证据类型而非训练比例，还给了降错方案。
在辛普森悖论设定下，增加预训练中干预样本比例并不能让模型正确判断因果方向，do()响应幅度增大但符号仍复制观察上下文。完全观察上下文在50个世界中29个出现符号反转，混合上下文19个，而仅对齐干预探针则41个正确。擦除上下文中的观察证据立即释放模型被压制的因果插值能力（ratio_true=+0.56）。在0.93B参数模型上，匹配探针仅干预分支的符号反转率为6%，而观察+干预分支为31.8%。作者提出证据平均协议，将符号错误从26%降至9%。
Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?
Interventional data is widely regarded as the gold standard for teaching models causal reasoning. We test this assumption in a fully controlled synthetic environment pitting observational correlation against causal effect, and find it fails instructively. In Simpson's-paradox worlds, where the two have systematically opposite signs, increasing the fraction of interventional samples in pretraining does not improve causal direction: the magnitude of the model's do()-response grows monotonically, yet its sign is copied from the observational context. What governs whether interventional evidence is used is not the training mixture but the evidence type present in the context at inference time. Under an identical training recipe, a purely observational context induces systematic sign reversal in 29/50 worlds, a mixed context in 19/50, while aligned interventional probes alone yield 41/50 correct. Erasing observational evidence from the context immediately releases the suppressed causal interpolation ability (ratio_true = +0.56); a four-state content manipulation shows the switch is content-mediated and graded. The suppression is stable across training seeds (11/11 strong reversals persist on a matched-protocol second seed) and robust as a rate at 0.93B parameters (31.8% vs. 6% reversals in the matched probe-only arm), even as absolute gains shrink four-fold. An external audit on CLadder exposes a learned positive-effect prior with a two-layer structure: sign-randomized retraining removes it in-distribution but not out-of-distribution. We summarize: the capability lives in the weights; the switch lives in the context, and activation patching localizes the switch to the middle layers' observational rows. We further quantify the sampling noise floor of probe-based causal evaluation and an evidence-averaging protocol that cuts sign errors from 26% to 9%.