DMCD: Semantic-Statistical Framework for Causal Discovery
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach
Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of interventions. While expert knowledge is required to construct principl…
Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
Causal discovery is an imperative foundation for decision-making across domains, such as smart health, AI for drug discovery and AIOps. Traditional statistical causal discovery methods, while well-established, predominan…
Causal DiscoveryCausal InferenceIRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data
Causal discovery is fundamental to scientific research, yet traditional statistical algorithms face significant challenges, including expensive data collection, redundant computation for known relations, and unrealistic …
LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems
Textual event records, such as alarm logs, have become an increasingly common data source in engineering and manufacturing systems. Beyond identifying correlations or recurring patterns, engineers are often interested in…
Multi-Agent Causal Discovery Using Large Language Models
Large Language Models (LLMs) have demonstrated significant potential in causal discovery tasks by utilizing their vast expert knowledge from extensive text corpora. However, the multi-agent capabilities of LLMs in causal…
Causal Discovery