Megadose AI progress, ranked and analyzed.

Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?

· ArXiv · AI/CL/LG ·
The paper finds that causal knowledge may be in the model, but observational context can flip how it is used.

In controlled Simpson’s-paradox settings, adding more interventional samples during pretraining did not by itself make models choose the correct causal direction. The decisive factor was the evidence type shown at inference: observational contexts often induced sign reversals, while aligned interventional probes performed much better. Removing observational evidence released a suppressed causal interpolation ability, and activation patching localized the switch to middle-layer observational rows. ArXiv · AI/CL/LG's note

score 4

Categories: Research