@inproceedings{sundararajan-2025-improving,
title = "Improving Factual Accuracy in Neural Data-to-Text Generation through Input Quality and Scalable Evaluation",
author = "Sundararajan, Barkavi",
editor = "Allen, Alyssa and
Feldhus, Nils and
Huidrom, Rudali and
Lorandi, Michela and
Sivaprasad, Adarsa and
Schmidtov{\'a}, Patr{\'i}cia",
booktitle = "Proceedings of the 1st Workshop for Young Researchers in Natural Language Generation",
month = oct,
year = "2025",
address = "Hanoi, Vietnam",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ynlg-main.3/",
pages = "10--16",
abstract = "Neural Language Models have become central to Natural Language Generation (NLG) research and can produce fluent and coherent text. However, when models generate text from complex, structured or long-form data such as tables or event logs, they often hallucinate and introduce factual errors. These hallucinations limit the practical deployment of large language models (LLMs) in applications where factual accuracy is critical. In my research, factual accuracy refers to the faithfulness of the generated text to the given input data. My PhD focuses on reducing hallucinations and improving factual accuracy in data-to-text generation, which I address through two core approaches: (i) analysing how input quality and structure improve factual accuracy, and (ii) developing a manual error annotation protocol and extending it into an LLM-as-Judge framework. This work aims to assess when automatic evaluation can complement human annotation and enable larger-scale evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sundararajan-2025-improving">
<titleInfo>
<title>Improving Factual Accuracy in Neural Data-to-Text Generation through Input Quality and Scalable Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barkavi</namePart>
<namePart type="family">Sundararajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop for Young Researchers in Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alyssa</namePart>
<namePart type="family">Allen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudali</namePart>
<namePart type="family">Huidrom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michela</namePart>
<namePart type="family">Lorandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adarsa</namePart>
<namePart type="family">Sivaprasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hanoi, Vietnam</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Language Models have become central to Natural Language Generation (NLG) research and can produce fluent and coherent text. However, when models generate text from complex, structured or long-form data such as tables or event logs, they often hallucinate and introduce factual errors. These hallucinations limit the practical deployment of large language models (LLMs) in applications where factual accuracy is critical. In my research, factual accuracy refers to the faithfulness of the generated text to the given input data. My PhD focuses on reducing hallucinations and improving factual accuracy in data-to-text generation, which I address through two core approaches: (i) analysing how input quality and structure improve factual accuracy, and (ii) developing a manual error annotation protocol and extending it into an LLM-as-Judge framework. This work aims to assess when automatic evaluation can complement human annotation and enable larger-scale evaluation.</abstract>
<identifier type="citekey">sundararajan-2025-improving</identifier>
<location>
<url>https://aclanthology.org/2025.ynlg-main.3/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>10</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Factual Accuracy in Neural Data-to-Text Generation through Input Quality and Scalable Evaluation
%A Sundararajan, Barkavi
%Y Allen, Alyssa
%Y Feldhus, Nils
%Y Huidrom, Rudali
%Y Lorandi, Michela
%Y Sivaprasad, Adarsa
%Y Schmidtová, Patrícia
%S Proceedings of the 1st Workshop for Young Researchers in Natural Language Generation
%D 2025
%8 October
%I Association for Computational Linguistics
%C Hanoi, Vietnam
%F sundararajan-2025-improving
%X Neural Language Models have become central to Natural Language Generation (NLG) research and can produce fluent and coherent text. However, when models generate text from complex, structured or long-form data such as tables or event logs, they often hallucinate and introduce factual errors. These hallucinations limit the practical deployment of large language models (LLMs) in applications where factual accuracy is critical. In my research, factual accuracy refers to the faithfulness of the generated text to the given input data. My PhD focuses on reducing hallucinations and improving factual accuracy in data-to-text generation, which I address through two core approaches: (i) analysing how input quality and structure improve factual accuracy, and (ii) developing a manual error annotation protocol and extending it into an LLM-as-Judge framework. This work aims to assess when automatic evaluation can complement human annotation and enable larger-scale evaluation.
%U https://aclanthology.org/2025.ynlg-main.3/
%P 10-16
Markdown (Informal)
[Improving Factual Accuracy in Neural Data-to-Text Generation through Input Quality and Scalable Evaluation](https://aclanthology.org/2025.ynlg-main.3/) (Sundararajan, YNLG 2025)
ACL