@inproceedings{di-bonaventura-etal-2024-explanation,
title = "Is Explanation All You Need? An Expert Survey on {LLM}-generated Explanations for Abusive Language Detection",
author = "Di Bonaventura, Chiara and
Siciliani, Lucia and
Basile, Pierpaolo and
Merono Penuela, Albert and
Mcgillivray, Barbara",
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-1.34/",
pages = "280--288",
ISBN = "979-12-210-7060-6",
abstract = "Explainable abusive language detection has proven to help both users and content moderators, and recent research has focused on prompting LLMs to generate explanations for why a specific text is hateful. Yet, understanding the alignment of these generated explanations with human expectations and judgements is far from being solved. In this paper, we design a before-and-after study recruiting AI experts to evaluate the usefulness and trustworthiness of LLM-generated explanations for abusive language detection tasks, investigating multiple LLMs and learning strategies. Our experiments show that expectations in terms of usefulness and trustworthiness of LLM-generated explanations are not met, as their ratings decrease by 47.78{\%} and 64.32{\%}, respectively, after treatment. Further, our results suggest caution in using LLMs for explanation generation of abusive language detection due to (i) their cultural bias, and (ii) difficulty in reliably evaluating them with empirical metrics. In light of our results, we provide three recommendations to use LLMs responsibly for explainable abusive language detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="di-bonaventura-etal-2024-explanation">
<titleInfo>
<title>Is Explanation All You Need? An Expert Survey on LLM-generated Explanations for Abusive Language Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Di Bonaventura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Siciliani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierpaolo</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Merono Penuela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Mcgillivray</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>Explainable abusive language detection has proven to help both users and content moderators, and recent research has focused on prompting LLMs to generate explanations for why a specific text is hateful. Yet, understanding the alignment of these generated explanations with human expectations and judgements is far from being solved. In this paper, we design a before-and-after study recruiting AI experts to evaluate the usefulness and trustworthiness of LLM-generated explanations for abusive language detection tasks, investigating multiple LLMs and learning strategies. Our experiments show that expectations in terms of usefulness and trustworthiness of LLM-generated explanations are not met, as their ratings decrease by 47.78% and 64.32%, respectively, after treatment. Further, our results suggest caution in using LLMs for explanation generation of abusive language detection due to (i) their cultural bias, and (ii) difficulty in reliably evaluating them with empirical metrics. In light of our results, we provide three recommendations to use LLMs responsibly for explainable abusive language detection.</abstract>
<identifier type="citekey">di-bonaventura-etal-2024-explanation</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.34/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>280</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is Explanation All You Need? An Expert Survey on LLM-generated Explanations for Abusive Language Detection
%A Di Bonaventura, Chiara
%A Siciliani, Lucia
%A Basile, Pierpaolo
%A Merono Penuela, Albert
%A Mcgillivray, Barbara
%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 di-bonaventura-etal-2024-explanation
%X Explainable abusive language detection has proven to help both users and content moderators, and recent research has focused on prompting LLMs to generate explanations for why a specific text is hateful. Yet, understanding the alignment of these generated explanations with human expectations and judgements is far from being solved. In this paper, we design a before-and-after study recruiting AI experts to evaluate the usefulness and trustworthiness of LLM-generated explanations for abusive language detection tasks, investigating multiple LLMs and learning strategies. Our experiments show that expectations in terms of usefulness and trustworthiness of LLM-generated explanations are not met, as their ratings decrease by 47.78% and 64.32%, respectively, after treatment. Further, our results suggest caution in using LLMs for explanation generation of abusive language detection due to (i) their cultural bias, and (ii) difficulty in reliably evaluating them with empirical metrics. In light of our results, we provide three recommendations to use LLMs responsibly for explainable abusive language detection.
%U https://aclanthology.org/2024.clicit-1.34/
%P 280-288
Markdown (Informal)
[Is Explanation All You Need? An Expert Survey on LLM-generated Explanations for Abusive Language Detection](https://aclanthology.org/2024.clicit-1.34/) (Di Bonaventura et al., CLiC-it 2024)
ACL