Exploratory Causal Inference in SAEnce
Abstract
Randomized Controlled Trials are one of the pillars of science; nevertheless, they rely on hand-crafted hypotheses and expensive analysis. Such constraints prevent causal effect estimation at scale, potentially anchoring on popular yet incomplete hypotheses. We propose to discover the unknown effects of a treatment directly from data. For this, we turn unstructured data from a trial into meaningful representations via pretrained foundation models and interpret them via a Sparse Auto Encoder. However, discovering significant causal effects at the neural level is not trivial due to multiple-testing issues and effects entanglement. To address these challenges, we introduce _Neural Effect Search_, a novel recursive procedure solving both issues by progressive stratification. After assessing the robustness of our algorithm on semi-synthetic experiments, we showcase, in the context of experimental ecology, the first successful unsupervised causal effect identification on a real-world scientific trial.
Cite
Text
Mencattini et al. "Exploratory Causal Inference in SAEnce." International Conference on Learning Representations, 2026.Markdown
[Mencattini et al. "Exploratory Causal Inference in SAEnce." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/mencattini2026iclr-exploratory/)BibTeX
@inproceedings{mencattini2026iclr-exploratory,
title = {{Exploratory Causal Inference in SAEnce}},
author = {Mencattini, Tommaso and Cadei, Riccardo and Locatello, Francesco},
booktitle = {International Conference on Learning Representations},
year = {2026},
url = {https://mlanthology.org/iclr/2026/mencattini2026iclr-exploratory/}
}