<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="isch-jennings-2026-narrative">
    <titleInfo>
        <title>Narrative License and Model Sycophancy in LLM Summaries of Scientific Work</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Calvin</namePart>
        <namePart type="family">Isch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Grace</namePart>
        <namePart type="family">Jennings</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are increasingly used to summarize academic work, yet model summaries can subtly exaggerate or mischaracterize findings. We examine how Narrative License (NL), rhetorical shifts that amplify claims beyond the underlying evidence, emerges in LLM summaries of scholarly articles. Using diverse prompting strategies across six leading models, we assess three dimensions of NL: causal overreach, rhetorical confidence, and sentiment (N = 100 peer-reviewed articles). Under basic summarization prompts, models frequently increase NL relative to academic abstracts; however, guardrail prompts can reduce these distortions. We further test how model “sycophancy” shapes NL, finding that stated stances and user personas produce predictable shifts in each element. These findings suggest that users and the benchmarks used to evaluate summarization should explicitly consider subtle rhetorical distortions and user alignment to ensure faithful scientific communication.</abstract>
    <identifier type="citekey">isch-jennings-2026-narrative</identifier>
    <identifier type="doi">10.18653/v1/2026.acl-long.746</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.746/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>16418</start>
            <end>16432</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Narrative License and Model Sycophancy in LLM Summaries of Scientific Work
%A Isch, Calvin
%A Jennings, Grace
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F isch-jennings-2026-narrative
%X Large language models (LLMs) are increasingly used to summarize academic work, yet model summaries can subtly exaggerate or mischaracterize findings. We examine how Narrative License (NL), rhetorical shifts that amplify claims beyond the underlying evidence, emerges in LLM summaries of scholarly articles. Using diverse prompting strategies across six leading models, we assess three dimensions of NL: causal overreach, rhetorical confidence, and sentiment (N = 100 peer-reviewed articles). Under basic summarization prompts, models frequently increase NL relative to academic abstracts; however, guardrail prompts can reduce these distortions. We further test how model “sycophancy” shapes NL, finding that stated stances and user personas produce predictable shifts in each element. These findings suggest that users and the benchmarks used to evaluate summarization should explicitly consider subtle rhetorical distortions and user alignment to ensure faithful scientific communication.
%R 10.18653/v1/2026.acl-long.746
%U https://aclanthology.org/2026.acl-long.746/
%U https://doi.org/10.18653/v1/2026.acl-long.746
%P 16418-16432

Markdown (Informal)

[Narrative License and Model Sycophancy in LLM Summaries of Scientific Work](https://aclanthology.org/2026.acl-long.746/) (Isch & Jennings, ACL 2026)

• Narrative License and Model Sycophancy in LLM Summaries of Scientific Work (Isch & Jennings, ACL 2026)

ACL

• Calvin Isch and Grace Jennings. 2026. Narrative License and Model Sycophancy in LLM Summaries of Scientific Work. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16418–16432, San Diego, California, United States. Association for Computational Linguistics.