@inproceedings{gili-etal-2024-veryfit,
title = "{V}eryf{IT} - Benchmark of Fact-Checked Claims for {I}talian: A {CALAMITA} Challenge",
author = "Gili, Jacopo and
Patti, Viviana and
Passaro, Lucia and
Caselli, Tommaso",
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-1.123/",
pages = "1116--1124",
ISBN = "979-12-210-7060-6",
abstract = "Achieving factual accuracy is a known pending issue for language models. Their design centered around the interactive component of user interaction and the extensive use of {\textquotedblleft}spontaneous{\textquotedblright} training data, has made them highly adept at conversational tasks but not fully reliable in terms of factual correctness. VeryfIT addresses this issue by evaluating the in-memory factual knowledge of language models on data written by professional fact-checkers, posing it as a true or false question.Topics of the statements vary but most are in specific domains related to the Italian government, policies, and social issues. The task presents several challenges: extracting statements from segments of speeches, determining appropriate contextual relevance both temporally and factually, and ultimately verifying the accuracy of the statements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gili-etal-2024-veryfit">
<titleInfo>
<title>VeryfIT - Benchmark of Fact-Checked Claims for Italian: A CALAMITA Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacopo</namePart>
<namePart type="family">Gili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Passaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Caselli</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>Achieving factual accuracy is a known pending issue for language models. Their design centered around the interactive component of user interaction and the extensive use of “spontaneous” training data, has made them highly adept at conversational tasks but not fully reliable in terms of factual correctness. VeryfIT addresses this issue by evaluating the in-memory factual knowledge of language models on data written by professional fact-checkers, posing it as a true or false question.Topics of the statements vary but most are in specific domains related to the Italian government, policies, and social issues. The task presents several challenges: extracting statements from segments of speeches, determining appropriate contextual relevance both temporally and factually, and ultimately verifying the accuracy of the statements.</abstract>
<identifier type="citekey">gili-etal-2024-veryfit</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.123/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>1116</start>
<end>1124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VeryfIT - Benchmark of Fact-Checked Claims for Italian: A CALAMITA Challenge
%A Gili, Jacopo
%A Patti, Viviana
%A Passaro, Lucia
%A Caselli, Tommaso
%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 gili-etal-2024-veryfit
%X Achieving factual accuracy is a known pending issue for language models. Their design centered around the interactive component of user interaction and the extensive use of “spontaneous” training data, has made them highly adept at conversational tasks but not fully reliable in terms of factual correctness. VeryfIT addresses this issue by evaluating the in-memory factual knowledge of language models on data written by professional fact-checkers, posing it as a true or false question.Topics of the statements vary but most are in specific domains related to the Italian government, policies, and social issues. The task presents several challenges: extracting statements from segments of speeches, determining appropriate contextual relevance both temporally and factually, and ultimately verifying the accuracy of the statements.
%U https://aclanthology.org/2024.clicit-1.123/
%P 1116-1124
Markdown (Informal)
[VeryfIT - Benchmark of Fact-Checked Claims for Italian: A CALAMITA Challenge](https://aclanthology.org/2024.clicit-1.123/) (Gili et al., CLiC-it 2024)
ACL