@inproceedings{li-etal-2026-dkcd,
title = "{DKCD}: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data",
author = "Li, Xin and
Li, Jin and
Wang, Shoujin and
Yu, Kun and
Chen, Fang",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.144/",
pages = "2824--2850",
ISBN = "979-8-89176-444-6",
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: (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, and (CH2) unreliable factor annotation, causing errors to propagate into the resulting graphs. To address these challenges, we introduce a novel Domain Knowledge-enhanced Causal Discovery framework (DKCD) for extracting causal graphs 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 causal reasoning. (2) Knowledge-guided Causal Reasoning: Reasoning with relevant knowledge discovers latent causal factors to address CH1 and generates causal clues for more accurate annotation to address CH2, and (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. The code and data are available at https://github.com/bigoldli329/DKCD."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-dkcd">
<titleInfo>
<title>DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoujin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<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: (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, and (CH2) unreliable factor annotation, causing errors to propagate into the resulting graphs. To address these challenges, we introduce a novel Domain Knowledge-enhanced Causal Discovery framework (DKCD) for extracting causal graphs 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 causal reasoning. (2) Knowledge-guided Causal Reasoning: Reasoning with relevant knowledge discovers latent causal factors to address CH1 and generates causal clues for more accurate annotation to address CH2, and (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. The code and data are available at https://github.com/bigoldli329/DKCD.</abstract>
<identifier type="citekey">li-etal-2026-dkcd</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.144/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2824</start>
<end>2850</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
%A Li, Xin
%A Li, Jin
%A Wang, Shoujin
%A Yu, Kun
%A Chen, Fang
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F li-etal-2026-dkcd
%X 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: (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, and (CH2) unreliable factor annotation, causing errors to propagate into the resulting graphs. To address these challenges, we introduce a novel Domain Knowledge-enhanced Causal Discovery framework (DKCD) for extracting causal graphs 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 causal reasoning. (2) Knowledge-guided Causal Reasoning: Reasoning with relevant knowledge discovers latent causal factors to address CH1 and generates causal clues for more accurate annotation to address CH2, and (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. The code and data are available at https://github.com/bigoldli329/DKCD.
%U https://aclanthology.org/2026.findings-aacl.144/
%P 2824-2850
Markdown (Informal)
[DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data](https://aclanthology.org/2026.findings-aacl.144/) (Li et al., Findings 2026)
ACL