@inproceedings{ostheimer-etal-2024-text,
title = "Text Style Transfer Evaluation Using Large Language Models",
author = "Ostheimer, Phil Sidney and
Nagda, Mayank Kumar and
Kloft, Marius and
Fellenz, Sophie",
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.1373/",
pages = "15802--15822",
abstract = "Evaluating Text Style Transfer (TST) is a complex task due to its multi-faceted nature. The quality of the generated text is measured based on challenging factors, such as style transfer accuracy, content preservation, and overall fluency. While human evaluation is considered to be the gold standard in TST assessment, it is costly and often hard to reproduce. Therefore, automated metrics are prevalent in these domains. Nonetheless, it is uncertain whether and to what extent these automated metrics correlate with human evaluations. Recent strides in Large Language Models (LLMs) have showcased their capacity to match and even exceed average human performance across diverse, unseen tasks. This suggests that LLMs could be a viable alternative to human evaluation and other automated metrics in TST evaluation. We compare the results of different LLMs in TST evaluation using multiple input prompts. Our findings highlight a strong correlation between (even zero-shot) prompting and human evaluation, showing that LLMs often outperform traditional automated metrics. Furthermore, we introduce the concept of prompt ensembling, demonstrating its ability to enhance the robustness of TST evaluation. This research contributes to the ongoing efforts for more robust and diverse evaluation methods by standardizing and validating TST evaluation with LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ostheimer-etal-2024-text">
<titleInfo>
<title>Text Style Transfer Evaluation Using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="given">Sidney</namePart>
<namePart type="family">Ostheimer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayank</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Nagda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marius</namePart>
<namePart type="family">Kloft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Fellenz</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>Evaluating Text Style Transfer (TST) is a complex task due to its multi-faceted nature. The quality of the generated text is measured based on challenging factors, such as style transfer accuracy, content preservation, and overall fluency. While human evaluation is considered to be the gold standard in TST assessment, it is costly and often hard to reproduce. Therefore, automated metrics are prevalent in these domains. Nonetheless, it is uncertain whether and to what extent these automated metrics correlate with human evaluations. Recent strides in Large Language Models (LLMs) have showcased their capacity to match and even exceed average human performance across diverse, unseen tasks. This suggests that LLMs could be a viable alternative to human evaluation and other automated metrics in TST evaluation. We compare the results of different LLMs in TST evaluation using multiple input prompts. Our findings highlight a strong correlation between (even zero-shot) prompting and human evaluation, showing that LLMs often outperform traditional automated metrics. Furthermore, we introduce the concept of prompt ensembling, demonstrating its ability to enhance the robustness of TST evaluation. This research contributes to the ongoing efforts for more robust and diverse evaluation methods by standardizing and validating TST evaluation with LLMs.</abstract>
<identifier type="citekey">ostheimer-etal-2024-text</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1373/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15802</start>
<end>15822</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Style Transfer Evaluation Using Large Language Models
%A Ostheimer, Phil Sidney
%A Nagda, Mayank Kumar
%A Kloft, Marius
%A Fellenz, Sophie
%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 ostheimer-etal-2024-text
%X Evaluating Text Style Transfer (TST) is a complex task due to its multi-faceted nature. The quality of the generated text is measured based on challenging factors, such as style transfer accuracy, content preservation, and overall fluency. While human evaluation is considered to be the gold standard in TST assessment, it is costly and often hard to reproduce. Therefore, automated metrics are prevalent in these domains. Nonetheless, it is uncertain whether and to what extent these automated metrics correlate with human evaluations. Recent strides in Large Language Models (LLMs) have showcased their capacity to match and even exceed average human performance across diverse, unseen tasks. This suggests that LLMs could be a viable alternative to human evaluation and other automated metrics in TST evaluation. We compare the results of different LLMs in TST evaluation using multiple input prompts. Our findings highlight a strong correlation between (even zero-shot) prompting and human evaluation, showing that LLMs often outperform traditional automated metrics. Furthermore, we introduce the concept of prompt ensembling, demonstrating its ability to enhance the robustness of TST evaluation. This research contributes to the ongoing efforts for more robust and diverse evaluation methods by standardizing and validating TST evaluation with LLMs.
%U https://aclanthology.org/2024.lrec-main.1373/
%P 15802-15822
Markdown (Informal)
[Text Style Transfer Evaluation Using Large Language Models](https://aclanthology.org/2024.lrec-main.1373/) (Ostheimer et al., LREC-COLING 2024)
ACL
- Phil Sidney Ostheimer, Mayank Kumar Nagda, Marius Kloft, and Sophie Fellenz. 2024. Text Style Transfer Evaluation Using Large Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15802–15822, Torino, Italia. ELRA and ICCL.