DMCD: Semantic-Statistical Framework for Causal Discovery
This work addresses causal structure learning for domains with metadata-rich data, offering a practical approach that combines semantic and statistical methods, though it is incremental as it builds on existing causal discovery techniques.
The paper tackles the problem of causal discovery by introducing DMCD, a framework that integrates LLM-based semantic drafting with statistical validation, achieving competitive or leading performance on real-world benchmarks with notable gains in recall and F1 score.
We present DMCD (DataMap Causal Discovery), a two-phase causal discovery framework that integrates LLM-based semantic drafting from variable metadata with statistical validation on observational data. In Phase I, a large language model proposes a sparse draft DAG, serving as a semantically informed prior over the space of possible causal structures. In Phase II, this draft is audited and refined via conditional independence testing, with detected discrepancies guiding targeted edge revisions. We evaluate our approach on three metadata-rich real-world benchmarks spanning industrial engineering, environmental monitoring, and IT systems analysis. Across these datasets, DMCD achieves competitive or leading performance against diverse causal discovery baselines, with particularly large gains in recall and F1 score. Probing and ablation experiments suggest that these improvements arise from semantic reasoning over metadata rather than memorization of benchmark graphs. Overall, our results demonstrate that combining semantic priors with principled statistical verification yields a high-performing and practically effective approach to causal structure learning.