# DMCD: Semantic-Statistical Framework for Causal Discovery

arXiv: https://arxiv.org/abs/2602.20333 · HTML: https://mlsanity.com/paper/2602.20333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 27 of 27)

- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [RLTF: Reinforcement Learning from Unit Test Feedback](https://mlsanity.com/paper/2307.04349/) (2023)
- [Deep End-to-end Causal Inference](https://mlsanity.com/paper/2202.02195/) (2022)
- [Can large language models build causal graphs?](https://mlsanity.com/paper/2303.05279/) (2023)
- [Causal Discovery with Language Models as Imperfect Experts](https://mlsanity.com/paper/2307.02390/) (2023)
- [Integrating Large Language Model for Improved Causal Discovery](https://mlsanity.com/paper/2306.16902/) (2023)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference](https://mlsanity.com/paper/2310.15117/) (2023)
- [CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery](https://mlsanity.com/paper/2310.01753/) (2023)
- [Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach](https://mlsanity.com/paper/2402.01454/) (2024)
- [Causal Inference with Large Language Model: A Survey](https://mlsanity.com/paper/2409.09822/) (2024)
- [Can Foundation Models Talk Causality?](https://mlsanity.com/paper/2206.10591/) (2022)
- [ALCM: Autonomous LLM-Augmented Causal Discovery Framework](https://mlsanity.com/paper/2405.01744/) (2024)
- [Large Language Models for Causal Discovery: Current Landscape and Future Directions](https://mlsanity.com/paper/2402.11068/) (2024)
- [Large Language Models are Effective Priors for Causal Graph Discovery](https://mlsanity.com/paper/2405.13551/) (2024)
- [pgmpy: A Python Toolkit for Bayesian Networks](https://mlsanity.com/paper/2304.08639/) (2023)
- [Causal Structure Learning Supervised by Large Language Model](https://mlsanity.com/paper/2311.11689/) (2023)
- [Case Studies of Causal Discovery from IT Monitoring Time Series](https://mlsanity.com/paper/2307.15678/) (2023)
- [RealTCD: Temporal Causal Discovery from Interventional Data with Large Language Model](https://mlsanity.com/paper/2404.14786/) (2024)
- [Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery](https://mlsanity.com/paper/2412.13667/) (2024)
- [CIPCaD-Bench: Continuous Industrial Process datasets for benchmarking Causal Discovery methods](https://mlsanity.com/paper/2208.01529/) (2022)
- [Interactive Causal Structure Discovery in Earth System Sciences](https://mlsanity.com/paper/2107.01126/) (2021)
- [LLM-initialized Differentiable Causal Discovery](https://mlsanity.com/paper/2410.21141/) (2024)
- [Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning](https://mlsanity.com/paper/2506.06093/) (2025)
- [A Simple Unified Approach to Testing High-Dimensional Conditional Independences for Categorical and Ordinal Data](https://mlsanity.com/paper/2206.04356/) (2022)
- [Large Language Models for Zero-shot Inference of Causal Structures in Biology](https://mlsanity.com/paper/2503.04347/) (2025)

## Abstract (arXiv)

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.