Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry

Le Qiu; Zhuan Anne Zhang; Hok Ming Adeline Chan; Emmanuele Chersoni

Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry

Le Qiu, Zhuan Anne Zhang, Hok Ming Adeline Chan, Emmanuele Chersoni

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Large Language Models (LLMs) are increasingly explored in the AEC (Architecture, Engineering, and Construction) domain, yet their reliability in regulatory tasks remains uncertain.

In this study, we focused on Hong Kong fire safety codes: together with domain experts, we create a localized dataset of multiple-choice (MCQs) and open-ended questions (OEQs) to evaluate 12 widely used LLMs, including both proprietary and open-source models.

Our findings show that proprietary models may achieve 80–90% accuracy on MCQs, while open-source models generally lag behind. On OEQ, humans and LLM judges rated the answers at 50-70% accuracy, suggesting that LLMs in specialized compliance tasks still have large margins of improvement.

Anthology ID:: 2026.lt4cpr-1.1
Volume:: Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response
Month:: November
Year:: 2026
Address:: Hengqin, China
Editors:: Belu Ticona, Fei Xia, William D. Lewis, Antonios Anastasopoulos
Venues:: LT4CPR | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 1–19
Language:
URL:: https://aclanthology.org/2026.lt4cpr-1.1/
DOI:
Bibkey:
Cite (ACL):: Le Qiu, Zhuan Anne Zhang, Hok Ming Adeline Chan, and Emmanuele Chersoni. 2026. Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry. In Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response, pages 1–19, Hengqin, China. Association for Computational Linguistics.
Cite (Informal):: Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry (Qiu et al., LT4CPR 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.lt4cpr-1.1.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{qiu-etal-2026-towards,
    title = "Towards a Benchmark for Fire Safety Code Interpretation in the {H}ong {K}ong {AEC} Industry",
    author = "Qiu, Le  and
      Zhang, Zhuan Anne  and
      Chan, Hok Ming Adeline  and
      Chersoni, Emmanuele",
    editor = "Ticona, Belu  and
      Xia, Fei  and
      Lewis, William D.  and
      Anastasopoulos, Antonios",
    booktitle = "Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.lt4cpr-1.1/",
    pages = "1--19",
    ISBN = "979-8-89176-450-7",
    abstract = "Large Language Models (LLMs) are increasingly explored in the AEC (Architecture, Engineering, and Construction) domain, yet their reliability in regulatory tasks remains uncertain.\par In this study, we focused on \textit{Hong Kong fire safety codes}: together with domain experts, we create a localized dataset of multiple-choice (MCQs) and open-ended questions (OEQs) to evaluate 12 widely used LLMs, including both proprietary and open-source models.\par Our findings show that proprietary models may achieve 80{--}90{\%} accuracy on MCQs, while open-source models generally lag behind. On OEQ, humans and LLM judges rated the answers at 50-70{\%} accuracy, suggesting that LLMs in specialized compliance tasks still have large margins of improvement."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-etal-2026-towards">
    <titleInfo>
        <title>Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Le</namePart>
        <namePart type="family">Qiu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhuan</namePart>
        <namePart type="given">Anne</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hok</namePart>
        <namePart type="given">Ming</namePart>
        <namePart type="given">Adeline</namePart>
        <namePart type="family">Chan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emmanuele</namePart>
        <namePart type="family">Chersoni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Belu</namePart>
            <namePart type="family">Ticona</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fei</namePart>
            <namePart type="family">Xia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">William</namePart>
            <namePart type="given">D</namePart>
            <namePart type="family">Lewis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonios</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-450-7</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) are increasingly explored in the AEC (Architecture, Engineering, and Construction) domain, yet their reliability in regulatory tasks remains uncertain.\par In this study, we focused on Hong Kong fire safety codes: together with domain experts, we create a localized dataset of multiple-choice (MCQs) and open-ended questions (OEQs) to evaluate 12 widely used LLMs, including both proprietary and open-source models.\par Our findings show that proprietary models may achieve 80–90% accuracy on MCQs, while open-source models generally lag behind. On OEQ, humans and LLM judges rated the answers at 50-70% accuracy, suggesting that LLMs in specialized compliance tasks still have large margins of improvement.</abstract>
    <identifier type="citekey">qiu-etal-2026-towards</identifier>
    <location>
        <url>https://aclanthology.org/2026.lt4cpr-1.1/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>1</start>
            <end>19</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry
%A Qiu, Le
%A Zhang, Zhuan Anne
%A Chan, Hok Ming Adeline
%A Chersoni, Emmanuele
%Y Ticona, Belu
%Y Xia, Fei
%Y Lewis, William D.
%Y Anastasopoulos, Antonios
%S Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-450-7
%F qiu-etal-2026-towards
%X Large Language Models (LLMs) are increasingly explored in the AEC (Architecture, Engineering, and Construction) domain, yet their reliability in regulatory tasks remains uncertain.\par In this study, we focused on Hong Kong fire safety codes: together with domain experts, we create a localized dataset of multiple-choice (MCQs) and open-ended questions (OEQs) to evaluate 12 widely used LLMs, including both proprietary and open-source models.\par Our findings show that proprietary models may achieve 80–90% accuracy on MCQs, while open-source models generally lag behind. On OEQ, humans and LLM judges rated the answers at 50-70% accuracy, suggesting that LLMs in specialized compliance tasks still have large margins of improvement.
%U https://aclanthology.org/2026.lt4cpr-1.1/
%P 1-19

Download as File

Markdown (Informal)

[Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry](https://aclanthology.org/2026.lt4cpr-1.1/) (Qiu et al., LT4CPR 2026)

Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry (Qiu et al., LT4CPR 2026)

ACL

Le Qiu, Zhuan Anne Zhang, Hok Ming Adeline Chan, and Emmanuele Chersoni. 2026. Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry. In Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response, pages 1–19, Hengqin, China. Association for Computational Linguistics.