@inproceedings{lopez-cortez-etal-2024-gmeg,
title = "{GMEG}-{EXP}: A Dataset of Human- and {LLM}-Generated Explanations of Grammatical and Fluency Edits",
author = "L{\'o}pez Cortez, S. Magal{\'i} and
Norris, Mark Josef and
Duman, Steve",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.688/",
pages = "7785--7800",
abstract = "Recent work has explored the ability of large language models (LLMs) to generate explanations of existing labeled data. In this work, we investigate the ability of LLMs to explain revisions in sentences. We introduce a new dataset demonstrating a novel task, which we call explaining text revisions. We collected human- and LLM-generated explanations of grammatical and fluency edits and defined criteria for the human evaluation of the explanations along three dimensions: Coverage, Informativeness, and Correctness. The results of a side-by-side evaluation show an Overall preference for human explanations, but there are many instances in which annotators show no preference. Annotators prefer human-generated explanations for Informativeness and Correctness, but they show no preference for Coverage. We also examined the extent to which the number of revisions in a sentence influences annotators' Overall preference for the explanations. We found that the preference for human explanations increases as the number of revisions in the sentence increases. Additionally, we show that the Overall preference for human explanations depends on the type of error being explained. We discuss explanation styles based on a qualitative analysis of 300 explanations. We release our dataset and annotation guidelines to encourage future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lopez-cortez-etal-2024-gmeg">
<titleInfo>
<title>GMEG-EXP: A Dataset of Human- and LLM-Generated Explanations of Grammatical and Fluency Edits</title>
</titleInfo>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="given">Magalí</namePart>
<namePart type="family">López Cortez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="given">Josef</namePart>
<namePart type="family">Norris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Duman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work has explored the ability of large language models (LLMs) to generate explanations of existing labeled data. In this work, we investigate the ability of LLMs to explain revisions in sentences. We introduce a new dataset demonstrating a novel task, which we call explaining text revisions. We collected human- and LLM-generated explanations of grammatical and fluency edits and defined criteria for the human evaluation of the explanations along three dimensions: Coverage, Informativeness, and Correctness. The results of a side-by-side evaluation show an Overall preference for human explanations, but there are many instances in which annotators show no preference. Annotators prefer human-generated explanations for Informativeness and Correctness, but they show no preference for Coverage. We also examined the extent to which the number of revisions in a sentence influences annotators’ Overall preference for the explanations. We found that the preference for human explanations increases as the number of revisions in the sentence increases. Additionally, we show that the Overall preference for human explanations depends on the type of error being explained. We discuss explanation styles based on a qualitative analysis of 300 explanations. We release our dataset and annotation guidelines to encourage future research.</abstract>
<identifier type="citekey">lopez-cortez-etal-2024-gmeg</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.688/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7785</start>
<end>7800</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GMEG-EXP: A Dataset of Human- and LLM-Generated Explanations of Grammatical and Fluency Edits
%A López Cortez, S. Magalí
%A Norris, Mark Josef
%A Duman, Steve
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lopez-cortez-etal-2024-gmeg
%X Recent work has explored the ability of large language models (LLMs) to generate explanations of existing labeled data. In this work, we investigate the ability of LLMs to explain revisions in sentences. We introduce a new dataset demonstrating a novel task, which we call explaining text revisions. We collected human- and LLM-generated explanations of grammatical and fluency edits and defined criteria for the human evaluation of the explanations along three dimensions: Coverage, Informativeness, and Correctness. The results of a side-by-side evaluation show an Overall preference for human explanations, but there are many instances in which annotators show no preference. Annotators prefer human-generated explanations for Informativeness and Correctness, but they show no preference for Coverage. We also examined the extent to which the number of revisions in a sentence influences annotators’ Overall preference for the explanations. We found that the preference for human explanations increases as the number of revisions in the sentence increases. Additionally, we show that the Overall preference for human explanations depends on the type of error being explained. We discuss explanation styles based on a qualitative analysis of 300 explanations. We release our dataset and annotation guidelines to encourage future research.
%U https://aclanthology.org/2024.lrec-main.688/
%P 7785-7800
Markdown (Informal)
[GMEG-EXP: A Dataset of Human- and LLM-Generated Explanations of Grammatical and Fluency Edits](https://aclanthology.org/2024.lrec-main.688/) (López Cortez et al., LREC-COLING 2024)
ACL