@inproceedings{yang-etal-2026-cautab,
title = "{C}au{T}ab: Counterfactual Tabular Data Synthesis with Functional and Causal-Dependency Constraints",
author = "Yang, Xingyu and
Ma, Mingchuan and
Xu, Dexuan and
Long, Xiangyang and
Huang, Yu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2390/",
pages = "54342--54363",
ISBN = "979-8-89176-459-0",
abstract = "High-quality tabular data is essential for data-driven tasks, yet often limited by scarcity and privacy concerns. While synthetic data generated by recent Deep Generative Models and LLMs improves fidelity, existing methods struggle to preserve rigorous attribute dependencies. As a result, the generated data may appear statistically realistic but lack logical consistency. To address this challenge, we propose CauTab, a novel counterfactual framework for tabular data synthesis that preserves functional dependencies and causal-dependency structures. CauTab operates in a three-stage pipeline: (1) it employs an LLM-guided mining strategy to efficiently identify functional dependencies; (2) it constructs a causal-dependency graph by integrating data-driven optimization with LLM-based semantic reasoning; and (3) it executes a dependency-constrained generation process via the Abduction-Intervention-Prediction paradigm. By enforcing deterministic constraints and using the learned graph for structured propagation, CauTab improves statistical fidelity while preserving logical consistency. Experiments demonstrate that CauTab outperforms baselines in data utility and fidelity, while maintaining competitive empirical privacy and strong logical consistency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-cautab">
<titleInfo>
<title>CauTab: Counterfactual Tabular Data Synthesis with Functional and Causal-Dependency Constraints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingyu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingchuan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dexuan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyang</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>High-quality tabular data is essential for data-driven tasks, yet often limited by scarcity and privacy concerns. While synthetic data generated by recent Deep Generative Models and LLMs improves fidelity, existing methods struggle to preserve rigorous attribute dependencies. As a result, the generated data may appear statistically realistic but lack logical consistency. To address this challenge, we propose CauTab, a novel counterfactual framework for tabular data synthesis that preserves functional dependencies and causal-dependency structures. CauTab operates in a three-stage pipeline: (1) it employs an LLM-guided mining strategy to efficiently identify functional dependencies; (2) it constructs a causal-dependency graph by integrating data-driven optimization with LLM-based semantic reasoning; and (3) it executes a dependency-constrained generation process via the Abduction-Intervention-Prediction paradigm. By enforcing deterministic constraints and using the learned graph for structured propagation, CauTab improves statistical fidelity while preserving logical consistency. Experiments demonstrate that CauTab outperforms baselines in data utility and fidelity, while maintaining competitive empirical privacy and strong logical consistency.</abstract>
<identifier type="citekey">yang-etal-2026-cautab</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2390/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>54342</start>
<end>54363</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CauTab: Counterfactual Tabular Data Synthesis with Functional and Causal-Dependency Constraints
%A Yang, Xingyu
%A Ma, Mingchuan
%A Xu, Dexuan
%A Long, Xiangyang
%A Huang, Yu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yang-etal-2026-cautab
%X High-quality tabular data is essential for data-driven tasks, yet often limited by scarcity and privacy concerns. While synthetic data generated by recent Deep Generative Models and LLMs improves fidelity, existing methods struggle to preserve rigorous attribute dependencies. As a result, the generated data may appear statistically realistic but lack logical consistency. To address this challenge, we propose CauTab, a novel counterfactual framework for tabular data synthesis that preserves functional dependencies and causal-dependency structures. CauTab operates in a three-stage pipeline: (1) it employs an LLM-guided mining strategy to efficiently identify functional dependencies; (2) it constructs a causal-dependency graph by integrating data-driven optimization with LLM-based semantic reasoning; and (3) it executes a dependency-constrained generation process via the Abduction-Intervention-Prediction paradigm. By enforcing deterministic constraints and using the learned graph for structured propagation, CauTab improves statistical fidelity while preserving logical consistency. Experiments demonstrate that CauTab outperforms baselines in data utility and fidelity, while maintaining competitive empirical privacy and strong logical consistency.
%U https://aclanthology.org/2026.emnlp-main.2390/
%P 54342-54363
Markdown (Informal)
[CauTab: Counterfactual Tabular Data Synthesis with Functional and Causal-Dependency Constraints](https://aclanthology.org/2026.emnlp-main.2390/) (Yang et al., EMNLP 2026)
ACL