Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales

Julie Jongeun Jung; Max Lu; Dogus Darici; Emilia Brüegge

Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales

Julie Jongeun Jung, Max Lu, Dogus Darici, Emilia Brüegge

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

Comparing LLM-human rater rationales using semantic similarity risks conflating textual proximity with evaluative agreement. We test whether embedding-based similarity reflects qualitative coding distinctions across rationale pairs in medical education. Similarity declined as rationale length differences grew and was less effective at distinguishing whether LLMs preserved the human’s central claim.

Anthology ID:: 2026.aimecon-main.52
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:: 466–471
Language:
URL:: https://aclanthology.org/2026.aimecon-main.52/
DOI:
Bibkey:
Cite (ACL):: Julie Jongeun Jung, Max Lu, Dogus Darici, and Emilia Brüegge. 2026. Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 466–471, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).
Cite (Informal):: Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales (Jung et al., AIME-Con 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.aimecon-main.52.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{jung-etal-2026-semantic,
    title = "Semantic Similarity is Not Enough for Comparing {LLM} and Human Rater Rationales",
    author = {Jung, Julie Jongeun  and
      Lu, Max  and
      Darici, Dogus  and
      Br{\"u}egge, Emilia},
    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.52/",
    pages = "466--471",
    ISBN = "979-8-9983004-0-0",
    abstract = "Comparing LLM-human rater rationales using semantic similarity risks conflating textual proximity with evaluative agreement. We test whether embedding-based similarity reflects qualitative coding distinctions across rationale pairs in medical education. Similarity declined as rationale length differences grew and was less effective at distinguishing whether LLMs preserved the human{'}s central claim."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-etal-2026-semantic">
    <titleInfo>
        <title>Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Julie</namePart>
        <namePart type="given">Jongeun</namePart>
        <namePart type="family">Jung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Max</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dogus</namePart>
        <namePart type="family">Darici</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emilia</namePart>
        <namePart type="family">Brüegge</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>Comparing LLM-human rater rationales using semantic similarity risks conflating textual proximity with evaluative agreement. We test whether embedding-based similarity reflects qualitative coding distinctions across rationale pairs in medical education. Similarity declined as rationale length differences grew and was less effective at distinguishing whether LLMs preserved the human’s central claim.</abstract>
    <identifier type="citekey">jung-etal-2026-semantic</identifier>
    <location>
        <url>https://aclanthology.org/2026.aimecon-main.52/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>466</start>
            <end>471</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales
%A Jung, Julie Jongeun
%A Lu, Max
%A Darici, Dogus
%A Brüegge, Emilia
%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 jung-etal-2026-semantic
%X Comparing LLM-human rater rationales using semantic similarity risks conflating textual proximity with evaluative agreement. We test whether embedding-based similarity reflects qualitative coding distinctions across rationale pairs in medical education. Similarity declined as rationale length differences grew and was less effective at distinguishing whether LLMs preserved the human’s central claim.
%U https://aclanthology.org/2026.aimecon-main.52/
%P 466-471

Download as File

Markdown (Informal)

[Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales](https://aclanthology.org/2026.aimecon-main.52/) (Jung et al., AIME-Con 2026)

Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales (Jung et al., AIME-Con 2026)

ACL

Julie Jongeun Jung, Max Lu, Dogus Darici, and Emilia Brüegge. 2026. Semantic Similarity is Not Enough for Comparing LLM and Human Rater Rationales. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 466–471, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).