@inproceedings{biggiogera-etal-2026-audq,
title = "{A}u{DQ}: Auditable Data Quality through Agentic Rule Discovery",
author = "Biggiogera, Jacopo and
Colombo, Nicolas and
Saxena, Krati and
Sarmah, Bhaskarjit and
Pasquali, Stefano",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.113/",
pages = "1925--1943",
ISBN = "979-8-89176-460-6",
abstract = "High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as the LLM-era automation raises expectations for traceability and accountability. We propose a vision for an ontology-grounded, repository-native data quality layer in which rules are first-class artifacts: versioned, provenance-linked to governance texts, and re-playable through immutable execution traces. As a first step toward validating this vision, we present a concrete implementation of its agentic rule-discovery core with two rule acquisition modes (Full-Agentic and Guided) and a human-in-the-loop (HITL) review interface. We define an evaluation framework and run experiments addressing whether our fully autonomous, divide-and-conquer agentic rule discovery produces rules of the same quality and diversity as those specified by a human expert, reporting preliminary results on two real world industry datasets in the finance and retail domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="biggiogera-etal-2026-audq">
<titleInfo>
<title>AuDQ: Auditable Data Quality through Agentic Rule Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacopo</namePart>
<namePart type="family">Biggiogera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Colombo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krati</namePart>
<namePart type="family">Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhaskarjit</namePart>
<namePart type="family">Sarmah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefano</namePart>
<namePart type="family">Pasquali</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as the LLM-era automation raises expectations for traceability and accountability. We propose a vision for an ontology-grounded, repository-native data quality layer in which rules are first-class artifacts: versioned, provenance-linked to governance texts, and re-playable through immutable execution traces. As a first step toward validating this vision, we present a concrete implementation of its agentic rule-discovery core with two rule acquisition modes (Full-Agentic and Guided) and a human-in-the-loop (HITL) review interface. We define an evaluation framework and run experiments addressing whether our fully autonomous, divide-and-conquer agentic rule discovery produces rules of the same quality and diversity as those specified by a human expert, reporting preliminary results on two real world industry datasets in the finance and retail domains.</abstract>
<identifier type="citekey">biggiogera-etal-2026-audq</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.113/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1925</start>
<end>1943</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AuDQ: Auditable Data Quality through Agentic Rule Discovery
%A Biggiogera, Jacopo
%A Colombo, Nicolas
%A Saxena, Krati
%A Sarmah, Bhaskarjit
%A Pasquali, Stefano
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F biggiogera-etal-2026-audq
%X High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as the LLM-era automation raises expectations for traceability and accountability. We propose a vision for an ontology-grounded, repository-native data quality layer in which rules are first-class artifacts: versioned, provenance-linked to governance texts, and re-playable through immutable execution traces. As a first step toward validating this vision, we present a concrete implementation of its agentic rule-discovery core with two rule acquisition modes (Full-Agentic and Guided) and a human-in-the-loop (HITL) review interface. We define an evaluation framework and run experiments addressing whether our fully autonomous, divide-and-conquer agentic rule discovery produces rules of the same quality and diversity as those specified by a human expert, reporting preliminary results on two real world industry datasets in the finance and retail domains.
%U https://aclanthology.org/2026.emnlp-industry.113/
%P 1925-1943
Markdown (Informal)
[AuDQ: Auditable Data Quality through Agentic Rule Discovery](https://aclanthology.org/2026.emnlp-industry.113/) (Biggiogera et al., EMNLP 2026)
ACL
- Jacopo Biggiogera, Nicolas Colombo, Krati Saxena, Bhaskarjit Sarmah, and Stefano Pasquali. 2026. AuDQ: Auditable Data Quality through Agentic Rule Discovery. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1925–1943, Budapest, Hungary. Association for Computational Linguistics.