@inproceedings{labruna-etal-2024-good,
title = "Are You a Good Assistant? Assessing {LLM} Trustability in Task-oriented Dialogues",
author = "Labruna, Tiziano and
Brenna, Sofia and
Bonetta, Giovanni and
Magnini, Bernardo",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.56/",
pages = "470--477",
ISBN = "979-12-210-7060-6",
abstract = "Despite the impressive capabilities of recent Large Language Models (LLMs) to generate human-like text, their ability to produce contextually appropriate content for specific communicative situations is still a matter of debate. This issue is particularly crucial when LLMs are employed as assistants to help solve tasks or achieve goals within a given conversational domain. In such scenarios, the assistant is expected to access specific knowledge (e.g., a database of restaurants, a calendar of appointments) that is not directly accessible to the user and must be consistently utilised to accomplish the task.In this paper, we conduct experiments to evaluate the trustworthiness of automatic assistants in task-oriented dialogues. Our findings indicate that state-of-the-art open-source LLMs still face significant challenges in maintaining logical consistency with a knowledge base of facts, highlighting the need for further advancements in this area."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="labruna-etal-2024-good">
<titleInfo>
<title>Are You a Good Assistant? Assessing LLM Trustability in Task-oriented Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tiziano</namePart>
<namePart type="family">Labruna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofia</namePart>
<namePart type="family">Brenna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Bonetta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernardo</namePart>
<namePart type="family">Magnini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>Despite the impressive capabilities of recent Large Language Models (LLMs) to generate human-like text, their ability to produce contextually appropriate content for specific communicative situations is still a matter of debate. This issue is particularly crucial when LLMs are employed as assistants to help solve tasks or achieve goals within a given conversational domain. In such scenarios, the assistant is expected to access specific knowledge (e.g., a database of restaurants, a calendar of appointments) that is not directly accessible to the user and must be consistently utilised to accomplish the task.In this paper, we conduct experiments to evaluate the trustworthiness of automatic assistants in task-oriented dialogues. Our findings indicate that state-of-the-art open-source LLMs still face significant challenges in maintaining logical consistency with a knowledge base of facts, highlighting the need for further advancements in this area.</abstract>
<identifier type="citekey">labruna-etal-2024-good</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.56/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>470</start>
<end>477</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are You a Good Assistant? Assessing LLM Trustability in Task-oriented Dialogues
%A Labruna, Tiziano
%A Brenna, Sofia
%A Bonetta, Giovanni
%A Magnini, Bernardo
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F labruna-etal-2024-good
%X Despite the impressive capabilities of recent Large Language Models (LLMs) to generate human-like text, their ability to produce contextually appropriate content for specific communicative situations is still a matter of debate. This issue is particularly crucial when LLMs are employed as assistants to help solve tasks or achieve goals within a given conversational domain. In such scenarios, the assistant is expected to access specific knowledge (e.g., a database of restaurants, a calendar of appointments) that is not directly accessible to the user and must be consistently utilised to accomplish the task.In this paper, we conduct experiments to evaluate the trustworthiness of automatic assistants in task-oriented dialogues. Our findings indicate that state-of-the-art open-source LLMs still face significant challenges in maintaining logical consistency with a knowledge base of facts, highlighting the need for further advancements in this area.
%U https://aclanthology.org/2024.clicit-1.56/
%P 470-477
Markdown (Informal)
[Are You a Good Assistant? Assessing LLM Trustability in Task-oriented Dialogues](https://aclanthology.org/2024.clicit-1.56/) (Labruna et al., CLiC-it 2024)
ACL