cs.AINov 10, 2026

When Should Semantic Priors Enter Partially-Identified Causal Discovery?

Authors: Muhammad Ahmed Mohsin, Saad Bin Ather, Valentin Six, Lancelot Da Costa, Tommaso Salvatori, Bernhard Scholkopf

Organizations: Stanford University · FAST-NUCES Lahore, Pakistan · University of Virginia Charlottesville, USA · VERSES Technologies Inc. · 

Abstract

Observational causal discovery often leaves causal di- rections unresolved or unstable. Large language mod- els (LLMs) can provide semantic information to resolve these directions, but incorrect proposals can exclude the true causal graph and invalidate downstream inference. We study three separate decisions: where to allocate semantic queries, which proposals to admit, and which causal graphs to retain. Our framework distinguishes population non-identifiability from finite-sample insta- bility, evaluates semantic orientation against statistical and random controls, and examines calibrated admis- sion and error-tolerant DAG retention. Experiments across benchmark networks show that semantic infor- mation improves recovery over coin-flip orientations, but targeting unstable edges has no established ad- vantage over matched-random allocation. The tested admission certificate cannot support nontrivial admis- sion with the available calibration tasks. Moreover, downstream retention depends on reference adequacy: learned references contain the true DAG in only three of 80 planned tasks. These findings separate the value of semantic information from the reliability of its alloca- tion, admission, and retention, and identify calibration size and reference adequacy as key limitations.

Figures & tables

Appendix figures & tables28 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Why LLMs Fail at Causal Discovery and How Interventional Agents Escape

    May 26, 2026Amartya Roy, Sonali ParbhooCausal DiscoveryCausal Reasoning in Language Models

  2. DMCD: Semantic-Statistical Framework for Causal Discovery

    Feb 23, 2026Samarth KaPatel, Sofia Nikiforova, Giacinto Paolo Saggese +1Causal DiscoveryCausal Structure Learning