@inproceedings{zaninello-magnini-2024-geese,
title = "{GEESE} - Generating and Evaluating Explanations for Semantic Entailment: A {CALAMITA} Challenge",
author = "Zaninello, Andrea 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-1.133/",
pages = "1209--1216",
ISBN = "979-12-210-7060-6",
abstract = "In the GEESE challenge, we present a pipeline to evaluate generated explanations for the task of Recognizing Textual Entailment (RTE) in Italian. The challenge focuses on evaluating the impact of generated explanations on the predictive performance of language models. Using a dataset enriched with human-written explanations, we employ two large language models (LLMs) to generate and utilize explanations for semantic relationships between sentence pairs. Our methodology assesses the quality of generated explanations by measuring changes in prediction accuracy when explanations are provided. Through reproducible experimentation, we establish benchmarks against various baseline approaches, demonstrating the potential of explanation injection to enhance model interpretability and performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaninello-magnini-2024-geese">
<titleInfo>
<title>GEESE - Generating and Evaluating Explanations for Semantic Entailment: A CALAMITA Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Zaninello</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>In the GEESE challenge, we present a pipeline to evaluate generated explanations for the task of Recognizing Textual Entailment (RTE) in Italian. The challenge focuses on evaluating the impact of generated explanations on the predictive performance of language models. Using a dataset enriched with human-written explanations, we employ two large language models (LLMs) to generate and utilize explanations for semantic relationships between sentence pairs. Our methodology assesses the quality of generated explanations by measuring changes in prediction accuracy when explanations are provided. Through reproducible experimentation, we establish benchmarks against various baseline approaches, demonstrating the potential of explanation injection to enhance model interpretability and performance.</abstract>
<identifier type="citekey">zaninello-magnini-2024-geese</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.133/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>1209</start>
<end>1216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GEESE - Generating and Evaluating Explanations for Semantic Entailment: A CALAMITA Challenge
%A Zaninello, Andrea
%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 zaninello-magnini-2024-geese
%X In the GEESE challenge, we present a pipeline to evaluate generated explanations for the task of Recognizing Textual Entailment (RTE) in Italian. The challenge focuses on evaluating the impact of generated explanations on the predictive performance of language models. Using a dataset enriched with human-written explanations, we employ two large language models (LLMs) to generate and utilize explanations for semantic relationships between sentence pairs. Our methodology assesses the quality of generated explanations by measuring changes in prediction accuracy when explanations are provided. Through reproducible experimentation, we establish benchmarks against various baseline approaches, demonstrating the potential of explanation injection to enhance model interpretability and performance.
%U https://aclanthology.org/2024.clicit-1.133/
%P 1209-1216
Markdown (Informal)
[GEESE - Generating and Evaluating Explanations for Semantic Entailment: A CALAMITA Challenge](https://aclanthology.org/2024.clicit-1.133/) (Zaninello & Magnini, CLiC-it 2024)
ACL