Publikation
Tags for DAGs: Graph Refinement with Meta-Informed Relations
Florian Peter Busch; Moritz Willig; Florian Guldan; Kristian Kersting; Devendra Singh Dhami
In: Transactions on Machine Learning Research (TMLR), Vol. 2026, Pages 1-52, arXiv, 2026.
Zusammenfassung
Causal discovery has shifted from data-centric methods to hybrid strategies that integrate
semantic knowledge from experts or large language models (LLMs). Such external informa-
tion is vital for identifying causal structures beyond the Markov Equivalence Class (MEC),
which data alone cannot resolve. However, expert availability is often limited, and LLMs
frequently misidentify causal directions in specialized domains. To overcome such short-
comings, we propose a tag-based approach that leverages semantically meaningful labels
while deriving causal directionality directly from data. Using variable-level tag assignments
from available sources (e.g., LLMs), our tags for DAGs method learns from identifiable
data structures to extract higher-level causal relations. These are then used to orient undi-
rected edges, enabling causal discovery to move beyond the MEC without reliance on fallible
external knowledge.