Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models

Dandan Chen Kaptur; Yue Huang; Yanhui Guo; Xuejun Ryan Ji

Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models

Dandan Chen Kaptur, Yue Huang, Yanhui Guo, Xuejun Ryan Ji

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

Prompting functions as a measurement condition that alters LLM coding behavior. We examined whether few-shot prompting improves GPT-based qualitative coding in systematic reviews. Contrary to expectations, we found that the zero-shot approach produced the highest agreement with human coders, suggesting increasing conservatism as more prompt structure was added.

Anthology ID:: 2026.aimecon-main.44
Volume:: Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
Month:: October
Year:: 2026
Address:: Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
Editors:: Joshua Wilson, Christopher Ormerod, Magdalen Beiting-Parrish
Venue:: AIME-Con
SIG:
Publisher:: National Council on Measurement in Education (NCME)
Note:
Pages:: 398–406
Language:
URL:: https://aclanthology.org/2026.aimecon-main.44/
DOI:
Bibkey:
Cite (ACL):: Dandan Chen Kaptur, Yue Huang, Yanhui Guo, and Xuejun Ryan Ji. 2026. Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 398–406, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).
Cite (Informal):: Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models (Kaptur et al., AIME-Con 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.aimecon-main.44.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{kaptur-etal-2026-prompting,
    title = "Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models",
    author = "Kaptur, Dandan Chen  and
      Huang, Yue  and
      Guo, Yanhui  and
      Ji, Xuejun Ryan",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting-Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Full Papers",
    month = oct,
    year = "2026",
    address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://aclanthology.org/2026.aimecon-main.44/",
    pages = "398--406",
    ISBN = "979-8-9983004-0-0",
    abstract = "Prompting functions as a measurement condition that alters LLM coding behavior. We examined whether few-shot prompting improves GPT-based qualitative coding in systematic reviews. Contrary to expectations, we found that the zero-shot approach produced the highest agreement with human coders, suggesting increasing conservatism as more prompt structure was added."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaptur-etal-2026-prompting">
    <titleInfo>
        <title>Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dandan</namePart>
        <namePart type="given">Chen</namePart>
        <namePart type="family">Kaptur</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanhui</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xuejun</namePart>
        <namePart type="given">Ryan</namePart>
        <namePart type="family">Ji</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 Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Joshua</namePart>
            <namePart type="family">Wilson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Ormerod</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Magdalen</namePart>
            <namePart type="family">Beiting-Parrish</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>National Council on Measurement in Education (NCME)</publisher>
            <place>
                <placeTerm type="text">Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-9983004-0-0</identifier>
    </relatedItem>
    <abstract>Prompting functions as a measurement condition that alters LLM coding behavior. We examined whether few-shot prompting improves GPT-based qualitative coding in systematic reviews. Contrary to expectations, we found that the zero-shot approach produced the highest agreement with human coders, suggesting increasing conservatism as more prompt structure was added.</abstract>
    <identifier type="citekey">kaptur-etal-2026-prompting</identifier>
    <location>
        <url>https://aclanthology.org/2026.aimecon-main.44/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>398</start>
            <end>406</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models
%A Kaptur, Dandan Chen
%A Huang, Yue
%A Guo, Yanhui
%A Ji, Xuejun Ryan
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-0-0
%F kaptur-etal-2026-prompting
%X Prompting functions as a measurement condition that alters LLM coding behavior. We examined whether few-shot prompting improves GPT-based qualitative coding in systematic reviews. Contrary to expectations, we found that the zero-shot approach produced the highest agreement with human coders, suggesting increasing conservatism as more prompt structure was added.
%U https://aclanthology.org/2026.aimecon-main.44/
%P 398-406

Download as File

Markdown (Informal)

[Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models](https://aclanthology.org/2026.aimecon-main.44/) (Kaptur et al., AIME-Con 2026)

Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models (Kaptur et al., AIME-Con 2026)

ACL

Dandan Chen Kaptur, Yue Huang, Yanhui Guo, and Xuejun Ryan Ji. 2026. Prompting as Measurement: Enhancing Coding for Systematic Reviews with Large Language Models. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 398–406, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).