@inproceedings{munker-etal-2026-next,
title = "Next Reply Prediction {X} ({NRP}-{X}) Dataset: Linguistic Discrepancies in Naively Generated Content",
author = {M{\"u}nker, Simon and
Schwager, Nils and
Kugler, Kai and
Heseltine, Michael and
Rettinger, Achim},
editor = "Montejo-Raez, Arturo and
Grisot, Cristina and
Blochowiak, Joanna and
Ljube{\v{s}}i{\'c}, Nikola and
Battaner, Elena and
Rigau, German",
booktitle = "Proceedings of Shaping Multilingual, Multimodal {AI} for the Social Sciences and Humanities ({LLM}s4{SSH}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma de Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.llms4ssh-1.5/",
doi = "10.63317/5fmgng5iobv6",
pages = "45--56",
abstract = "The increasing use of Large Language Models (LLMs) as proxies for human participants in social science research presents a promising, yet methodologically risky, paradigm shift. While LLMs offer scalability and cost-efficiency, their ``naive'' application, where they are prompted to generate content without explicit behavioral constraints, introduces significant linguistic discrepancies that challenge the validity of research findings. This paper addresses these limitations by introducing a novel, history-conditioned reply prediction task on authentic X (formerly Twitter) data, to create a dataset designed to evaluate the linguistic output of LLMs against human-generated content. We analyze these discrepancies using stylistic and content-based metrics, providing a quantitative framework for researchers to assess the quality and authenticity of synthetic data. Our findings highlight the need for more sophisticated prompting techniques and specialized datasets to ensure that LLM-generated content accurately reflects the complex linguistic patterns of human communication, thereby improving the validity of computational social science studies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="munker-etal-2026-next">
<titleInfo>
<title>Next Reply Prediction X (NRP-X) Dataset: Linguistic Discrepancies in Naively Generated Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Münker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Schwager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Kugler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Heseltine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Achim</namePart>
<namePart type="family">Rettinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Grisot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Blochowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The increasing use of Large Language Models (LLMs) as proxies for human participants in social science research presents a promising, yet methodologically risky, paradigm shift. While LLMs offer scalability and cost-efficiency, their “naive” application, where they are prompted to generate content without explicit behavioral constraints, introduces significant linguistic discrepancies that challenge the validity of research findings. This paper addresses these limitations by introducing a novel, history-conditioned reply prediction task on authentic X (formerly Twitter) data, to create a dataset designed to evaluate the linguistic output of LLMs against human-generated content. We analyze these discrepancies using stylistic and content-based metrics, providing a quantitative framework for researchers to assess the quality and authenticity of synthetic data. Our findings highlight the need for more sophisticated prompting techniques and specialized datasets to ensure that LLM-generated content accurately reflects the complex linguistic patterns of human communication, thereby improving the validity of computational social science studies.</abstract>
<identifier type="citekey">munker-etal-2026-next</identifier>
<identifier type="doi">10.63317/5fmgng5iobv6</identifier>
<location>
<url>https://aclanthology.org/2026.llms4ssh-1.5/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>45</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Next Reply Prediction X (NRP-X) Dataset: Linguistic Discrepancies in Naively Generated Content
%A Münker, Simon
%A Schwager, Nils
%A Kugler, Kai
%A Heseltine, Michael
%A Rettinger, Achim
%Y Montejo-Raez, Arturo
%Y Grisot, Cristina
%Y Blochowiak, Joanna
%Y Ljubešić, Nikola
%Y Battaner, Elena
%Y Rigau, German
%S Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca (Spain)
%F munker-etal-2026-next
%X The increasing use of Large Language Models (LLMs) as proxies for human participants in social science research presents a promising, yet methodologically risky, paradigm shift. While LLMs offer scalability and cost-efficiency, their “naive” application, where they are prompted to generate content without explicit behavioral constraints, introduces significant linguistic discrepancies that challenge the validity of research findings. This paper addresses these limitations by introducing a novel, history-conditioned reply prediction task on authentic X (formerly Twitter) data, to create a dataset designed to evaluate the linguistic output of LLMs against human-generated content. We analyze these discrepancies using stylistic and content-based metrics, providing a quantitative framework for researchers to assess the quality and authenticity of synthetic data. Our findings highlight the need for more sophisticated prompting techniques and specialized datasets to ensure that LLM-generated content accurately reflects the complex linguistic patterns of human communication, thereby improving the validity of computational social science studies.
%R 10.63317/5fmgng5iobv6
%U https://aclanthology.org/2026.llms4ssh-1.5/
%U https://doi.org/10.63317/5fmgng5iobv6
%P 45-56
Markdown (Informal)
[Next Reply Prediction X (NRP-X) Dataset: Linguistic Discrepancies in Naively Generated Content](https://aclanthology.org/2026.llms4ssh-1.5/) (Münker et al., LLMs4SSH 2026)
ACL