@inproceedings{dobler-etal-2024-trust,
title = "Can {I} trust You? {LLM}s as conversational agents",
author = {D{\"o}bler, Marc and
Mahendravarman, Raghavendran and
Moskvina, Anna and
Saef, Nasrin},
editor = "Deshpande, Ameet and
Hwang, EunJeong and
Murahari, Vishvak and
Park, Joon Sung and
Yang, Diyi and
Sabharwal, Ashish and
Narasimhan, Karthik and
Kalyan, Ashwin",
booktitle = "Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024)",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.personalize-1.5",
pages = "71--75",
abstract = "With the rising popularity of LLMs in the public sphere, they become more and more attractive as a tool for doing one{'}s own research without having to rely on search engines or specialized knowledge of a scientific field. But using LLMs as a source for factual information can lead one to fall prey to misinformation or hallucinations dreamed up by the model. In this paper we examine the gpt-4 LLM by simulating a large number of potential research queries and evaluate how many of the generated references are factually correct as well as existent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dobler-etal-2024-trust">
<titleInfo>
<title>Can I trust You? LLMs as conversational agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Döbler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghavendran</namePart>
<namePart type="family">Mahendravarman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Moskvina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nasrin</namePart>
<namePart type="family">Saef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ameet</namePart>
<namePart type="family">Deshpande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">EunJeong</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishvak</namePart>
<namePart type="family">Murahari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joon</namePart>
<namePart type="given">Sung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Sabharwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Narasimhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwin</namePart>
<namePart type="family">Kalyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the rising popularity of LLMs in the public sphere, they become more and more attractive as a tool for doing one’s own research without having to rely on search engines or specialized knowledge of a scientific field. But using LLMs as a source for factual information can lead one to fall prey to misinformation or hallucinations dreamed up by the model. In this paper we examine the gpt-4 LLM by simulating a large number of potential research queries and evaluate how many of the generated references are factually correct as well as existent.</abstract>
<identifier type="citekey">dobler-etal-2024-trust</identifier>
<location>
<url>https://aclanthology.org/2024.personalize-1.5</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>71</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can I trust You? LLMs as conversational agents
%A Döbler, Marc
%A Mahendravarman, Raghavendran
%A Moskvina, Anna
%A Saef, Nasrin
%Y Deshpande, Ameet
%Y Hwang, EunJeong
%Y Murahari, Vishvak
%Y Park, Joon Sung
%Y Yang, Diyi
%Y Sabharwal, Ashish
%Y Narasimhan, Karthik
%Y Kalyan, Ashwin
%S Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F dobler-etal-2024-trust
%X With the rising popularity of LLMs in the public sphere, they become more and more attractive as a tool for doing one’s own research without having to rely on search engines or specialized knowledge of a scientific field. But using LLMs as a source for factual information can lead one to fall prey to misinformation or hallucinations dreamed up by the model. In this paper we examine the gpt-4 LLM by simulating a large number of potential research queries and evaluate how many of the generated references are factually correct as well as existent.
%U https://aclanthology.org/2024.personalize-1.5
%P 71-75
Markdown (Informal)
[Can I trust You? LLMs as conversational agents](https://aclanthology.org/2024.personalize-1.5) (Döbler et al., PERSONALIZE-WS 2024)
ACL
- Marc Döbler, Raghavendran Mahendravarman, Anna Moskvina, and Nasrin Saef. 2024. Can I trust You? LLMs as conversational agents. In Proceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024), pages 71–75, St. Julians, Malta. Association for Computational Linguistics.