@inproceedings{amin-etal-2026-spark,
title = "{SP}ar{K}-Eval: Evaluating Structure-Aware Knowledge Acquisition in {LLM}s for Domain Adaptation to Industrial Records",
author = "Amin, Ekant Muljibhai and
Koreeda, Yuta and
Sogawa, Yasuhiro",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1221/",
doi = "10.18653/v1/2026.findings-acl.1221",
pages = "24403--24418",
ISBN = "979-8-89176-395-1",
abstract = "Large Language Models (LLMs) often underperform in domain adaptation for industrial settings, where available corpora are limited and structurally diverse. These corpora frequently include non-natural formats such as tables, entity lists, or bullet-point instructions that hinder effective learning. To understand and improve domain-adaptive pretraining on such data, we introduce SParK-Eval (Structure-aware Parametric Knowledge Evaluation), a framework that constructs question{--}answer pairs from pretraining data and annotates each with its input structure (e.g., natural sentence, table, list). This enables fine-grained analysis of how input structure affects parametric knowledge acquisition during DAPT. Additionally, we propose a prompt-based input normalization method that converts diverse inputs into coherent natural sentences, providing a reference for isolating structural effects. Our experiments show that LLMs acquire substantially more knowledge from natural sentences than from their structurally non-standard counterparts. These findings underscore the importance of structure-aware evaluation in diagnosing learning challenges and guiding effective domain adaptation strategies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amin-etal-2026-spark">
<titleInfo>
<title>SParK-Eval: Evaluating Structure-Aware Knowledge Acquisition in LLMs for Domain Adaptation to Industrial Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekant</namePart>
<namePart type="given">Muljibhai</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Koreeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhiro</namePart>
<namePart type="family">Sogawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) often underperform in domain adaptation for industrial settings, where available corpora are limited and structurally diverse. These corpora frequently include non-natural formats such as tables, entity lists, or bullet-point instructions that hinder effective learning. To understand and improve domain-adaptive pretraining on such data, we introduce SParK-Eval (Structure-aware Parametric Knowledge Evaluation), a framework that constructs question–answer pairs from pretraining data and annotates each with its input structure (e.g., natural sentence, table, list). This enables fine-grained analysis of how input structure affects parametric knowledge acquisition during DAPT. Additionally, we propose a prompt-based input normalization method that converts diverse inputs into coherent natural sentences, providing a reference for isolating structural effects. Our experiments show that LLMs acquire substantially more knowledge from natural sentences than from their structurally non-standard counterparts. These findings underscore the importance of structure-aware evaluation in diagnosing learning challenges and guiding effective domain adaptation strategies.</abstract>
<identifier type="citekey">amin-etal-2026-spark</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1221</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1221/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>24403</start>
<end>24418</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SParK-Eval: Evaluating Structure-Aware Knowledge Acquisition in LLMs for Domain Adaptation to Industrial Records
%A Amin, Ekant Muljibhai
%A Koreeda, Yuta
%A Sogawa, Yasuhiro
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F amin-etal-2026-spark
%X Large Language Models (LLMs) often underperform in domain adaptation for industrial settings, where available corpora are limited and structurally diverse. These corpora frequently include non-natural formats such as tables, entity lists, or bullet-point instructions that hinder effective learning. To understand and improve domain-adaptive pretraining on such data, we introduce SParK-Eval (Structure-aware Parametric Knowledge Evaluation), a framework that constructs question–answer pairs from pretraining data and annotates each with its input structure (e.g., natural sentence, table, list). This enables fine-grained analysis of how input structure affects parametric knowledge acquisition during DAPT. Additionally, we propose a prompt-based input normalization method that converts diverse inputs into coherent natural sentences, providing a reference for isolating structural effects. Our experiments show that LLMs acquire substantially more knowledge from natural sentences than from their structurally non-standard counterparts. These findings underscore the importance of structure-aware evaluation in diagnosing learning challenges and guiding effective domain adaptation strategies.
%R 10.18653/v1/2026.findings-acl.1221
%U https://aclanthology.org/2026.findings-acl.1221/
%U https://doi.org/10.18653/v1/2026.findings-acl.1221
%P 24403-24418
Markdown (Informal)
[SParK-Eval: Evaluating Structure-Aware Knowledge Acquisition in LLMs for Domain Adaptation to Industrial Records](https://aclanthology.org/2026.findings-acl.1221/) (Amin et al., Findings 2026)
ACL