@inproceedings{trienes-etal-2024-infolossqa,
title = "{I}nfo{L}oss{QA}: Characterizing and Recovering Information Loss in Text Simplification",
author = {Trienes, Jan and
Joseph, Sebastian and
Schl{\"o}tterer, J{\"o}rg and
Seifert, Christin and
Lo, Kyle and
Xu, Wei and
Wallace, Byron and
Li, Junyi Jessy},
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.234",
doi = "10.18653/v1/2024.acl-long.234",
pages = "4263--4294",
abstract = "Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness. This work proposes InfoLossQA, a framework to characterize and recover simplification-induced information loss in form of question-and-answer (QA) pairs. Building on the theory of Questions Under Discussion, the QA pairs are designed to help readers deepen their knowledge of a text. First, we collect a dataset of 1,000 linguist-curated QA pairs derived from 104 LLM simplifications of English medical study abstracts. Our analyses of this data reveal that information loss occurs frequently, and that the QA pairs give a high-level overview of what information was lost. Second, we devise two methods for this task: end-to-end prompting of open-source and commercial language models, and a natural language inference pipeline. With a novel evaluation framework considering the correctness of QA pairs and their linguistic suitability, our expert evaluation reveals that models struggle to reliably identify information loss and applying similar standards as humans at what constitutes information loss.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trienes-etal-2024-infolossqa">
<titleInfo>
<title>InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Trienes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Joseph</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Schlötterer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christin</namePart>
<namePart type="family">Seifert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byron</namePart>
<namePart type="family">Wallace</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness. This work proposes InfoLossQA, a framework to characterize and recover simplification-induced information loss in form of question-and-answer (QA) pairs. Building on the theory of Questions Under Discussion, the QA pairs are designed to help readers deepen their knowledge of a text. First, we collect a dataset of 1,000 linguist-curated QA pairs derived from 104 LLM simplifications of English medical study abstracts. Our analyses of this data reveal that information loss occurs frequently, and that the QA pairs give a high-level overview of what information was lost. Second, we devise two methods for this task: end-to-end prompting of open-source and commercial language models, and a natural language inference pipeline. With a novel evaluation framework considering the correctness of QA pairs and their linguistic suitability, our expert evaluation reveals that models struggle to reliably identify information loss and applying similar standards as humans at what constitutes information loss.</abstract>
<identifier type="citekey">trienes-etal-2024-infolossqa</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.234</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.234</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4263</start>
<end>4294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification
%A Trienes, Jan
%A Joseph, Sebastian
%A Schlötterer, Jörg
%A Seifert, Christin
%A Lo, Kyle
%A Xu, Wei
%A Wallace, Byron
%A Li, Junyi Jessy
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F trienes-etal-2024-infolossqa
%X Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness. This work proposes InfoLossQA, a framework to characterize and recover simplification-induced information loss in form of question-and-answer (QA) pairs. Building on the theory of Questions Under Discussion, the QA pairs are designed to help readers deepen their knowledge of a text. First, we collect a dataset of 1,000 linguist-curated QA pairs derived from 104 LLM simplifications of English medical study abstracts. Our analyses of this data reveal that information loss occurs frequently, and that the QA pairs give a high-level overview of what information was lost. Second, we devise two methods for this task: end-to-end prompting of open-source and commercial language models, and a natural language inference pipeline. With a novel evaluation framework considering the correctness of QA pairs and their linguistic suitability, our expert evaluation reveals that models struggle to reliably identify information loss and applying similar standards as humans at what constitutes information loss.
%R 10.18653/v1/2024.acl-long.234
%U https://aclanthology.org/2024.acl-long.234
%U https://doi.org/10.18653/v1/2024.acl-long.234
%P 4263-4294
Markdown (Informal)
[InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification](https://aclanthology.org/2024.acl-long.234) (Trienes et al., ACL 2024)
ACL
- Jan Trienes, Sebastian Joseph, Jörg Schlötterer, Christin Seifert, Kyle Lo, Wei Xu, Byron Wallace, and Junyi Jessy Li. 2024. InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4263–4294, Bangkok, Thailand. Association for Computational Linguistics.