# CauTion preprint reports reliable causal discovery through selective LLM use

_Published Monday, October 19, 2026 at 8:31 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report that CauTion, a framework for inferring causal relationships from observational data, resolves up to 96% of relationships through agreement among statistical algorithms, with near-perfect accuracy on that agreed subset. The preprint reports better results than statistical and LLM-assisted baselines across six datasets.

The framework estimates the relative reliability of a language model and the statistical algorithms without requiring annotations. It uses that estimate to weight votes, restricting language-model arbitration to relationships where algorithmic evidence is unreliable. A final repair step removes cycles from the resulting causal graph. The near-perfect accuracy finding applies to the consensus subset, not the entire graph.

## Sources

- [cs.LG updates on arXiv.org](https://arxiv.org/abs/2606.03602)

---
Canonical: https://techandbusiness.org/newswire/4KsqYtTucmPkAe5GNAZb2x
Published: 2026-10-19T12:31:52.155Z
Story chronology: 2026-10-19T04:00:00.000Z
Retrieved: 2026-10-19T15:01:49.718Z
Publisher: Tech & Business (techandbusiness.org)