@inproceedings{devasier-etal-2026-frame,
title = "Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Data",
author = "Devasier, Jacob and
Putta, Akshith and
Wang, Qing and
Moses, Alankrit and
Li, Chengkai",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.136/",
doi = "10.63317/23pcoy44ykq9",
pages = "1721--1731",
abstract = "Automated fact-checking benchmarks have largely ignored the challenge of verifying claims against real-world, high-volume structured data, instead focusing on small, curated tables. We introduce a new large-scale, multilingual dataset to address this critical gap. It contains 78,503 synthetic claims grounded in 434 complex OECD tables, which average over 500K rows each. We propose a novel, frame-guided methodology where algorithms programmatically select significant data points based on six semantic frames to generate realistic claims in English, Chinese, Spanish, and Hindi. Crucially, we demonstrate through knowledge-probing experiments that LLMs have not memorized these facts, forcing systems to perform genuine retrieval and reasoning rather than relying on parameterized knowledge. We provide a baseline SQL-generation system and show that our benchmark is highly challenging. Our analysis identifies evidence retrieval as the primary bottleneck, with models struggling to find the correct data in massive tables. This dataset provides a critical new resource for advancing research on this unsolved, real-world problem."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devasier-etal-2026-frame">
<titleInfo>
<title>Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Devasier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshith</namePart>
<namePart type="family">Putta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alankrit</namePart>
<namePart type="family">Moses</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengkai</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated fact-checking benchmarks have largely ignored the challenge of verifying claims against real-world, high-volume structured data, instead focusing on small, curated tables. We introduce a new large-scale, multilingual dataset to address this critical gap. It contains 78,503 synthetic claims grounded in 434 complex OECD tables, which average over 500K rows each. We propose a novel, frame-guided methodology where algorithms programmatically select significant data points based on six semantic frames to generate realistic claims in English, Chinese, Spanish, and Hindi. Crucially, we demonstrate through knowledge-probing experiments that LLMs have not memorized these facts, forcing systems to perform genuine retrieval and reasoning rather than relying on parameterized knowledge. We provide a baseline SQL-generation system and show that our benchmark is highly challenging. Our analysis identifies evidence retrieval as the primary bottleneck, with models struggling to find the correct data in massive tables. This dataset provides a critical new resource for advancing research on this unsolved, real-world problem.</abstract>
<identifier type="citekey">devasier-etal-2026-frame</identifier>
<identifier type="doi">10.63317/23pcoy44ykq9</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.136/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1721</start>
<end>1731</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Data
%A Devasier, Jacob
%A Putta, Akshith
%A Wang, Qing
%A Moses, Alankrit
%A Li, Chengkai
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F devasier-etal-2026-frame
%X Automated fact-checking benchmarks have largely ignored the challenge of verifying claims against real-world, high-volume structured data, instead focusing on small, curated tables. We introduce a new large-scale, multilingual dataset to address this critical gap. It contains 78,503 synthetic claims grounded in 434 complex OECD tables, which average over 500K rows each. We propose a novel, frame-guided methodology where algorithms programmatically select significant data points based on six semantic frames to generate realistic claims in English, Chinese, Spanish, and Hindi. Crucially, we demonstrate through knowledge-probing experiments that LLMs have not memorized these facts, forcing systems to perform genuine retrieval and reasoning rather than relying on parameterized knowledge. We provide a baseline SQL-generation system and show that our benchmark is highly challenging. Our analysis identifies evidence retrieval as the primary bottleneck, with models struggling to find the correct data in massive tables. This dataset provides a critical new resource for advancing research on this unsolved, real-world problem.
%R 10.63317/23pcoy44ykq9
%U https://aclanthology.org/2026.lrec-1.136/
%U https://doi.org/10.63317/23pcoy44ykq9
%P 1721-1731
Markdown (Informal)
[Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Data](https://aclanthology.org/2026.lrec-1.136/) (Devasier et al., LREC 2026)
ACL