DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
2026-07-10 • Computation and Language
Computation and Language
AI summaryⓘ
The authors developed a new method called DKCD to find cause-and-effect relationships in complex fields like healthcare and finance using unstructured data. Their approach uses three steps: first, it finds important domain knowledge; second, it uses that knowledge to discover hidden factors and improve data labeling; third, it builds a map of cause-effect links based on this better information. Their experiments show this approach finds more accurate causal factors and graphs than previous methods. This helps deal with the challenges of missing hidden information and unreliable labeling in specialized domains.
causal discoveryunstructured datalatent factorsdomain knowledgelarge language modelscausal reasoningcausal graphsknowledge miningdata annotationhigh-expertise domains
Authors
Xin Li, Jin Li, Shoujin Wang, Kun Yu, Fang Chen
Abstract
Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models (LLMs) to identify causal factors from unstructured data and annotate them into structured data for causal graph construction. However, they remain limited by two key challenges (CHs): (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, due to the lack of domain-specific knowledge; and (CH2) unreliable factor annotation, caused by the lack of domain-grounded reasoning, which propagates errors to the resulting causal graphs. To address these challenges, we introduce a novel Domain Knowledge-enhanced Causal Discovery framework (DKCD) for causal discovery from unstructured data in high-expertise domains with three interconnected components: (1) Knowledge Mining: It retrieves relevant domain knowledge based on observable factors to support subsequent causal reasoning. (2) Knowledge-guided Causal Reasoning: Reasoning with relevant knowledge, it discovers latent causal factors to address CH1 and generates key causal clues for more accurate data annotation to address CH2. (3) Causal Structure Discovery: It constructs the final causal graphs based on a more complete factor set and accurate annotations. Experiments on two domain-specific datasets show that DKCD significantly improves both causal factor identification and causal graph construction.