@inproceedings{dzhubaeva-etal-2025-unstructured,
title = "Unstructured Minds, Predictable Machines: A Comparative Study of Narrative Cohesion in Human and {LLM} Stream-of-Consciousness Writing",
author = "Dzhubaeva, Nellia and
Trinley, Katharina and
Pissani, Laura",
editor = "Zhao, Jin and
Wang, Mingyang and
Liu, Zhu",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-srw.85/",
doi = "10.18653/v1/2025.acl-srw.85",
pages = "1079--1096",
ISBN = "979-8-89176-254-1",
abstract = "This paper examines differences between stream-of-consciousness (SoC) narratives written by humans and those generated by large language models (LLMs) to assess narrative coherence and personality expression. We generated texts by prompting LLMs (Llama-3.1-8B {\&} DeepSeek-R1-Distill-Llama-8B) with the first half of SoC-essays while either providing the models with the personality characteristics (Big Five) or omitting them. Our analysis revealed consistently low similarity between LLM-generated continuations and original human texts, as measured by cosine similarity, perplexity, and BLEU scores. Including explicit personality traits significantly enhanced Llama-3.1-8B{'}s performance, particularly in BLEU scores.Further analysis of personality expression showed varying alignment patterns between LLMs and human texts. Specifically, Llama-3.1-8B exhibited higher extraversion but low agreeableness, while DeepSeek-R1-Distill-Llama-8B displayed dramatic personality shifts during its reasoning process, especially when prompted with personality traits, with all models consistently showing very low Openness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dzhubaeva-etal-2025-unstructured">
<titleInfo>
<title>Unstructured Minds, Predictable Machines: A Comparative Study of Narrative Cohesion in Human and LLM Stream-of-Consciousness Writing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nellia</namePart>
<namePart type="family">Dzhubaeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Trinley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Pissani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-254-1</identifier>
</relatedItem>
<abstract>This paper examines differences between stream-of-consciousness (SoC) narratives written by humans and those generated by large language models (LLMs) to assess narrative coherence and personality expression. We generated texts by prompting LLMs (Llama-3.1-8B & DeepSeek-R1-Distill-Llama-8B) with the first half of SoC-essays while either providing the models with the personality characteristics (Big Five) or omitting them. Our analysis revealed consistently low similarity between LLM-generated continuations and original human texts, as measured by cosine similarity, perplexity, and BLEU scores. Including explicit personality traits significantly enhanced Llama-3.1-8B’s performance, particularly in BLEU scores.Further analysis of personality expression showed varying alignment patterns between LLMs and human texts. Specifically, Llama-3.1-8B exhibited higher extraversion but low agreeableness, while DeepSeek-R1-Distill-Llama-8B displayed dramatic personality shifts during its reasoning process, especially when prompted with personality traits, with all models consistently showing very low Openness.</abstract>
<identifier type="citekey">dzhubaeva-etal-2025-unstructured</identifier>
<identifier type="doi">10.18653/v1/2025.acl-srw.85</identifier>
<location>
<url>https://aclanthology.org/2025.acl-srw.85/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1079</start>
<end>1096</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unstructured Minds, Predictable Machines: A Comparative Study of Narrative Cohesion in Human and LLM Stream-of-Consciousness Writing
%A Dzhubaeva, Nellia
%A Trinley, Katharina
%A Pissani, Laura
%Y Zhao, Jin
%Y Wang, Mingyang
%Y Liu, Zhu
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-254-1
%F dzhubaeva-etal-2025-unstructured
%X This paper examines differences between stream-of-consciousness (SoC) narratives written by humans and those generated by large language models (LLMs) to assess narrative coherence and personality expression. We generated texts by prompting LLMs (Llama-3.1-8B & DeepSeek-R1-Distill-Llama-8B) with the first half of SoC-essays while either providing the models with the personality characteristics (Big Five) or omitting them. Our analysis revealed consistently low similarity between LLM-generated continuations and original human texts, as measured by cosine similarity, perplexity, and BLEU scores. Including explicit personality traits significantly enhanced Llama-3.1-8B’s performance, particularly in BLEU scores.Further analysis of personality expression showed varying alignment patterns between LLMs and human texts. Specifically, Llama-3.1-8B exhibited higher extraversion but low agreeableness, while DeepSeek-R1-Distill-Llama-8B displayed dramatic personality shifts during its reasoning process, especially when prompted with personality traits, with all models consistently showing very low Openness.
%R 10.18653/v1/2025.acl-srw.85
%U https://aclanthology.org/2025.acl-srw.85/
%U https://doi.org/10.18653/v1/2025.acl-srw.85
%P 1079-1096
Markdown (Informal)
[Unstructured Minds, Predictable Machines: A Comparative Study of Narrative Cohesion in Human and LLM Stream-of-Consciousness Writing](https://aclanthology.org/2025.acl-srw.85/) (Dzhubaeva et al., ACL 2025)
ACL