<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siskou-hautli-janisz-2025-exploring">
    <titleInfo>
        <title>Exploring the Limits of Prompting LLMs with Speaker-Specific Rhetorical Fingerprints</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wassiliki</namePart>
        <namePart type="family">Siskou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Annette</namePart>
        <namePart type="family">Hautli-Janisz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Isuri</namePart>
            <namePart type="given">Nanomi</namePart>
            <namePart type="family">Arachchige</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Francesca</namePart>
            <namePart type="family">Frontini</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Paul</namePart>
            <namePart type="family">Rayson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The capabilities of Large Language Models (LLMs) to mimic written content are being tested on a wide range of tasks and settings, from persuasive essays to programming code. However, the question to what extent they are capable of mimicking human conversational monologue is less well-researched. In this study, we explore the limits of popular LLMs in impersonating content in a high-stakes legal setting, namely for the generation of the decision statement in parole suitability hearings: We distill a linguistically well-motivated rhetorical fingerprint from individual presiding commissioners, based on patterns observed in verbatim transcripts and then enhance the model prompts with those characteristics. When comparing this enhanced prompt with an underspecified prompt we show that LLMs can approximate certain rhetorical features when prompted accordingly, but are not able to fully replicate the linguistic profile of the original speakers as their own fingerprint dominates.</abstract>
    <identifier type="citekey">siskou-hautli-janisz-2025-exploring</identifier>
    <location>
        <url>https://aclanthology.org/2025.lm4dh-1.14/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>143</start>
            <end>154</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploring the Limits of Prompting LLMs with Speaker-Specific Rhetorical Fingerprints
%A Siskou, Wassiliki
%A Hautli-Janisz, Annette
%Y Arachchige, Isuri Nanomi
%Y Frontini, Francesca
%Y Mitkov, Ruslan
%Y Rayson, Paul
%S Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F siskou-hautli-janisz-2025-exploring
%X The capabilities of Large Language Models (LLMs) to mimic written content are being tested on a wide range of tasks and settings, from persuasive essays to programming code. However, the question to what extent they are capable of mimicking human conversational monologue is less well-researched. In this study, we explore the limits of popular LLMs in impersonating content in a high-stakes legal setting, namely for the generation of the decision statement in parole suitability hearings: We distill a linguistically well-motivated rhetorical fingerprint from individual presiding commissioners, based on patterns observed in verbatim transcripts and then enhance the model prompts with those characteristics. When comparing this enhanced prompt with an underspecified prompt we show that LLMs can approximate certain rhetorical features when prompted accordingly, but are not able to fully replicate the linguistic profile of the original speakers as their own fingerprint dominates.
%U https://aclanthology.org/2025.lm4dh-1.14/
%P 143-154

Markdown (Informal)

[Exploring the Limits of Prompting LLMs with Speaker-Specific Rhetorical Fingerprints](https://aclanthology.org/2025.lm4dh-1.14/) (Siskou & Hautli-Janisz, LM4DH 2025)

• Exploring the Limits of Prompting LLMs with Speaker-Specific Rhetorical Fingerprints (Siskou & Hautli-Janisz, LM4DH 2025)

ACL

• Wassiliki Siskou and Annette Hautli-Janisz. 2025. Exploring the Limits of Prompting LLMs with Speaker-Specific Rhetorical Fingerprints. In Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities, pages 143–154, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.