@inproceedings{fundal-etal-2026-humans,
title = "Humans Introduce, Models Elaborate: Asymmetric Narrative Agency in Human-{LLM} Co-Writing",
author = "Fundal, Halfdan Nordahl and
Bizzoni, Yuri and
Bilde, Charlotte Gj{\o}rup and
Johannesen, Ida B{\ae}kke and
Baglini, Rebekah Brita",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2002/",
pages = "45603--45617",
ISBN = "979-8-89176-459-0",
abstract = "Human{--}LLM co-writing is increasingly used for open-ended text generation, but much prior work focuses on final outputs rather than the interactional dynamics through which stories are produced. We study turn-based collaborative storytelling across three matched conditions: Human{--}Human (HH), Human{--}AI (HA), and AI{--}AI (AA). Using a shared storytelling paradigm, we measure how agents align, introduce novel material, and influence narrative development through turn-level measures of valence adaptation, semantic novelty, transience, and resonance. Our results show that HA co-writing is not intermediate between HH and AA collaboration. Instead, it displays a distinctive asymmetry where humans tend to introduce more novel and persistent narrative material, while LLMs tend to elaborate and stabilize the existing context. These findings suggest that, in this setting, LLMs function less as human co-authors and more as adaptive narrative amplifiers that reshape how agency is distributed in collaborative writing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fundal-etal-2026-humans">
<titleInfo>
<title>Humans Introduce, Models Elaborate: Asymmetric Narrative Agency in Human-LLM Co-Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Halfdan</namePart>
<namePart type="given">Nordahl</namePart>
<namePart type="family">Fundal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlotte</namePart>
<namePart type="given">Gjørup</namePart>
<namePart type="family">Bilde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ida</namePart>
<namePart type="given">Bække</namePart>
<namePart type="family">Johannesen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebekah</namePart>
<namePart type="given">Brita</namePart>
<namePart type="family">Baglini</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Human–LLM co-writing is increasingly used for open-ended text generation, but much prior work focuses on final outputs rather than the interactional dynamics through which stories are produced. We study turn-based collaborative storytelling across three matched conditions: Human–Human (HH), Human–AI (HA), and AI–AI (AA). Using a shared storytelling paradigm, we measure how agents align, introduce novel material, and influence narrative development through turn-level measures of valence adaptation, semantic novelty, transience, and resonance. Our results show that HA co-writing is not intermediate between HH and AA collaboration. Instead, it displays a distinctive asymmetry where humans tend to introduce more novel and persistent narrative material, while LLMs tend to elaborate and stabilize the existing context. These findings suggest that, in this setting, LLMs function less as human co-authors and more as adaptive narrative amplifiers that reshape how agency is distributed in collaborative writing.</abstract>
<identifier type="citekey">fundal-etal-2026-humans</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2002/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>45603</start>
<end>45617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Humans Introduce, Models Elaborate: Asymmetric Narrative Agency in Human-LLM Co-Writing
%A Fundal, Halfdan Nordahl
%A Bizzoni, Yuri
%A Bilde, Charlotte Gjørup
%A Johannesen, Ida Bække
%A Baglini, Rebekah Brita
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F fundal-etal-2026-humans
%X Human–LLM co-writing is increasingly used for open-ended text generation, but much prior work focuses on final outputs rather than the interactional dynamics through which stories are produced. We study turn-based collaborative storytelling across three matched conditions: Human–Human (HH), Human–AI (HA), and AI–AI (AA). Using a shared storytelling paradigm, we measure how agents align, introduce novel material, and influence narrative development through turn-level measures of valence adaptation, semantic novelty, transience, and resonance. Our results show that HA co-writing is not intermediate between HH and AA collaboration. Instead, it displays a distinctive asymmetry where humans tend to introduce more novel and persistent narrative material, while LLMs tend to elaborate and stabilize the existing context. These findings suggest that, in this setting, LLMs function less as human co-authors and more as adaptive narrative amplifiers that reshape how agency is distributed in collaborative writing.
%U https://aclanthology.org/2026.emnlp-main.2002/
%P 45603-45617
Markdown (Informal)
[Humans Introduce, Models Elaborate: Asymmetric Narrative Agency in Human-LLM Co-Writing](https://aclanthology.org/2026.emnlp-main.2002/) (Fundal et al., EMNLP 2026)
ACL