@inproceedings{yanjie-etal-2026-cemlit,
title = "{C}em{L}it-{IE}: Schema-Constrained {LLM} Extraction for Traceable Cement Strength Databases",
author = "Yanjie, Sun and
Hong, Mengze and
Zhang, Chen Jason and
LI, Haoyang",
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.98/",
pages = "1663--1673",
ISBN = "979-8-89176-460-6",
abstract = "Cementitious materials teams need machine-readable databases of compressive strength records to support mix-design optimization. However, manual curation of the literature is too slow and hard to scale. We present CemLit-IE, a five-stage zero-shot pipeline, converting raw PDFs into fully attributed records with provenance. The core challenge is that the relevant information is distributed across tables, text, and figures. Even though table-only extraction produces plausible numbers, the results are not auditable. CemLit-IE addresses this through a series of methods, including keyword-weighted page scoring, structured table injection, value-provenance schema, and review queue. On a benchmark of 20 papers with 655 expert-annotated records, CemLit-IE achieves a recall of 76.3{\%} with 99.2{\%} precision and 100{\%} exact-match accuracy in a text-only model. The recall can be raised to 83.5{\%} when figure reading is enabled. The ablation study shows that each design choice contributes to improving precision. As for the cost, a separate 270-paper journal-batch run extracted 2,039 strength records at {\$}31.28 total API cost. All data and code are publicly released."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yanjie-etal-2026-cemlit">
<titleInfo>
<title>CemLit-IE: Schema-Constrained LLM Extraction for Traceable Cement Strength Databases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Yanjie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengze</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="given">Jason</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyang</namePart>
<namePart type="family">LI</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>Cementitious materials teams need machine-readable databases of compressive strength records to support mix-design optimization. However, manual curation of the literature is too slow and hard to scale. We present CemLit-IE, a five-stage zero-shot pipeline, converting raw PDFs into fully attributed records with provenance. The core challenge is that the relevant information is distributed across tables, text, and figures. Even though table-only extraction produces plausible numbers, the results are not auditable. CemLit-IE addresses this through a series of methods, including keyword-weighted page scoring, structured table injection, value-provenance schema, and review queue. On a benchmark of 20 papers with 655 expert-annotated records, CemLit-IE achieves a recall of 76.3% with 99.2% precision and 100% exact-match accuracy in a text-only model. The recall can be raised to 83.5% when figure reading is enabled. The ablation study shows that each design choice contributes to improving precision. As for the cost, a separate 270-paper journal-batch run extracted 2,039 strength records at $31.28 total API cost. All data and code are publicly released.</abstract>
<identifier type="citekey">yanjie-etal-2026-cemlit</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.98/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1663</start>
<end>1673</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CemLit-IE: Schema-Constrained LLM Extraction for Traceable Cement Strength Databases
%A Yanjie, Sun
%A Hong, Mengze
%A Zhang, Chen Jason
%A LI, Haoyang
%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 yanjie-etal-2026-cemlit
%X Cementitious materials teams need machine-readable databases of compressive strength records to support mix-design optimization. However, manual curation of the literature is too slow and hard to scale. We present CemLit-IE, a five-stage zero-shot pipeline, converting raw PDFs into fully attributed records with provenance. The core challenge is that the relevant information is distributed across tables, text, and figures. Even though table-only extraction produces plausible numbers, the results are not auditable. CemLit-IE addresses this through a series of methods, including keyword-weighted page scoring, structured table injection, value-provenance schema, and review queue. On a benchmark of 20 papers with 655 expert-annotated records, CemLit-IE achieves a recall of 76.3% with 99.2% precision and 100% exact-match accuracy in a text-only model. The recall can be raised to 83.5% when figure reading is enabled. The ablation study shows that each design choice contributes to improving precision. As for the cost, a separate 270-paper journal-batch run extracted 2,039 strength records at $31.28 total API cost. All data and code are publicly released.
%U https://aclanthology.org/2026.emnlp-industry.98/
%P 1663-1673
Markdown (Informal)
[CemLit-IE: Schema-Constrained LLM Extraction for Traceable Cement Strength Databases](https://aclanthology.org/2026.emnlp-industry.98/) (Yanjie et al., EMNLP 2026)
ACL