<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahnert-etal-2026-survey">
    <titleInfo>
        <title>Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Georg</namePart>
        <namePart type="family">Ahnert</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anna-Carolina</namePart>
        <namePart type="family">Haensch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Barbara</namePart>
        <namePart type="family">Plank</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Markus</namePart>
        <namePart type="family">Strohmaier</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>Many _in-silico_ simulations of human survey responses with large language models (LLMs) focus on generating closed-ended survey responses, whereas LLMs are typically trained to generate open-ended text instead. Previous research has used a diverse range of methods for generating closed-ended survey responses with LLMs and a standard practice remains to be identified. In this paper, we systematically investigate the impact that various **Survey Response Generation Methods** have on predicted survey responses. We present the results of 32 mio. simulated survey responses across 8 Survey Response Generation Methods, 4 political attitude surveys, and 10 open-weight language models. We find significant differences between the Survey Response Generation Methods in both individual-level and subpopulation-level alignment. Our results show that Restricted Generation Methods perform best overall, and that reasoning output does not consistently improve alignment. Our work underlines the significant impact that Survey Response Generation Methods have on simulated survey responses, and we develop practical recommendations on the application of Survey Response Generation Methods.</abstract>
    <identifier type="citekey">ahnert-etal-2026-survey</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1927/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>41554</start>
            <end>41577</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models
%A Ahnert, Georg
%A Haensch, Anna-Carolina
%A Plank, Barbara
%A Strohmaier, Markus
%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 ahnert-etal-2026-survey
%X Many _in-silico_ simulations of human survey responses with large language models (LLMs) focus on generating closed-ended survey responses, whereas LLMs are typically trained to generate open-ended text instead. Previous research has used a diverse range of methods for generating closed-ended survey responses with LLMs and a standard practice remains to be identified. In this paper, we systematically investigate the impact that various **Survey Response Generation Methods** have on predicted survey responses. We present the results of 32 mio. simulated survey responses across 8 Survey Response Generation Methods, 4 political attitude surveys, and 10 open-weight language models. We find significant differences between the Survey Response Generation Methods in both individual-level and subpopulation-level alignment. Our results show that Restricted Generation Methods perform best overall, and that reasoning output does not consistently improve alignment. Our work underlines the significant impact that Survey Response Generation Methods have on simulated survey responses, and we develop practical recommendations on the application of Survey Response Generation Methods.
%U https://aclanthology.org/2026.acl-long.1927/
%P 41554-41577

Markdown (Informal)

[Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models](https://aclanthology.org/2026.acl-long.1927/) (Ahnert et al., ACL 2026)

• Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models (Ahnert et al., ACL 2026)

ACL

• Georg Ahnert, Anna-Carolina Haensch, Barbara Plank, and Markus Strohmaier. 2026. Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 41554–41577, San Diego, California, United States. Association for Computational Linguistics.