@inproceedings{arnold-grobner-2026-large,
title = "Do Large Language Models appeal to the Senses? Narrative Embodiment in Stories told by {L}lama and {Q}wen",
author = {Arnold, Stefan and
Gr{\"o}bner, Rene},
editor = "Arad, Dana and
Belinkov, Yonatan and
Chen, Hanjie and
Feldhus, Nils and
Mueller, Aaron and
Mohebbi, Hosein and
Sarti, Gabriele and
Tutek, Martin",
booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.blackboxnlp-1.22/",
pages = "368--373",
ISBN = "979-8-89176-476-7",
abstract = "Language Models (LMs) produce highly fluent narratives, yet cognitive probing suggests their semantic representations lack grounding in sensorimotor experiences. By projecting model-generated texts into a multidimensional sensorimotor vector space, we quantify narrative embodiment in storytelling. Specifically, we evaluate the impact of parameter scaling and conditional multimodality on perceptual grounding. We find that (1) model capacity monotonically widens the divergence from the human level of embodiment, demonstrating that scale alone cannot resolve narrative disembodiment, and (2) audio-language models demonstrate a distinct superiority over vision-language models, an effect we contextualize through the auditory scaffolding hypothesis. Ultimately, we demonstrate that authentic sensorimotor grounding is not an emergent property of autoregressive decoding or conditional encoding, highlighting a critical limitation in current generative architectures."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arnold-grobner-2026-large">
<titleInfo>
<title>Do Large Language Models appeal to the Senses? Narrative Embodiment in Stories told by Llama and Qwen</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Arnold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rene</namePart>
<namePart type="family">Gröbner</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 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tutek</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">979-8-89176-476-7</identifier>
</relatedItem>
<abstract>Language Models (LMs) produce highly fluent narratives, yet cognitive probing suggests their semantic representations lack grounding in sensorimotor experiences. By projecting model-generated texts into a multidimensional sensorimotor vector space, we quantify narrative embodiment in storytelling. Specifically, we evaluate the impact of parameter scaling and conditional multimodality on perceptual grounding. We find that (1) model capacity monotonically widens the divergence from the human level of embodiment, demonstrating that scale alone cannot resolve narrative disembodiment, and (2) audio-language models demonstrate a distinct superiority over vision-language models, an effect we contextualize through the auditory scaffolding hypothesis. Ultimately, we demonstrate that authentic sensorimotor grounding is not an emergent property of autoregressive decoding or conditional encoding, highlighting a critical limitation in current generative architectures.</abstract>
<identifier type="citekey">arnold-grobner-2026-large</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.22/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>368</start>
<end>373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Large Language Models appeal to the Senses? Narrative Embodiment in Stories told by Llama and Qwen
%A Arnold, Stefan
%A Gröbner, Rene
%Y Arad, Dana
%Y Belinkov, Yonatan
%Y Chen, Hanjie
%Y Feldhus, Nils
%Y Mueller, Aaron
%Y Mohebbi, Hosein
%Y Sarti, Gabriele
%Y Tutek, Martin
%S Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-476-7
%F arnold-grobner-2026-large
%X Language Models (LMs) produce highly fluent narratives, yet cognitive probing suggests their semantic representations lack grounding in sensorimotor experiences. By projecting model-generated texts into a multidimensional sensorimotor vector space, we quantify narrative embodiment in storytelling. Specifically, we evaluate the impact of parameter scaling and conditional multimodality on perceptual grounding. We find that (1) model capacity monotonically widens the divergence from the human level of embodiment, demonstrating that scale alone cannot resolve narrative disembodiment, and (2) audio-language models demonstrate a distinct superiority over vision-language models, an effect we contextualize through the auditory scaffolding hypothesis. Ultimately, we demonstrate that authentic sensorimotor grounding is not an emergent property of autoregressive decoding or conditional encoding, highlighting a critical limitation in current generative architectures.
%U https://aclanthology.org/2026.blackboxnlp-1.22/
%P 368-373
Markdown (Informal)
[Do Large Language Models appeal to the Senses? Narrative Embodiment in Stories told by Llama and Qwen](https://aclanthology.org/2026.blackboxnlp-1.22/) (Arnold & Gröbner, BlackboxNLP 2026)
ACL