@inproceedings{michail-etal-2025-paraphrasus,
title = "{PARAPHRASUS}: A Comprehensive Benchmark for Evaluating Paraphrase Detection Models",
author = "Michail, Andrianos and
Clematide, Simon and
Opitz, Juri",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.585/",
pages = "8749--8762",
abstract = "The task of determining whether two texts are paraphrases has long been a challenge in NLP. However, the prevailing notion of paraphrase is often quite simplistic, offering only a limited view of the vast spectrum of paraphrase phenomena. Indeed, we find that evaluating models in a paraphrase dataset can leave uncertainty about their true semantic understanding. To alleviate this, we create PARAPHRASUS, a benchmark designed for multi-dimensional assessment, benchmarking and selection of paraphrase detection models. We find that paraphrase detection models under our fine-grained evaluation lens exhibit trade-offs that cannot be captured through a single classification dataset. Furthermore, PARAPHRASUS allows prompt calibration for different use cases, tailoring LLM models to specific strictness levels. PARAPHRASUS includes 3 challenges spanning over 10 datasets, including 8 repurposed and 2 newly annotated; we release it along with a benchmarking library at https://github.com/impresso/paraphrasus"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="michail-etal-2025-paraphrasus">
<titleInfo>
<title>PARAPHRASUS: A Comprehensive Benchmark for Evaluating Paraphrase Detection Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrianos</namePart>
<namePart type="family">Michail</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juri</namePart>
<namePart type="family">Opitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of determining whether two texts are paraphrases has long been a challenge in NLP. However, the prevailing notion of paraphrase is often quite simplistic, offering only a limited view of the vast spectrum of paraphrase phenomena. Indeed, we find that evaluating models in a paraphrase dataset can leave uncertainty about their true semantic understanding. To alleviate this, we create PARAPHRASUS, a benchmark designed for multi-dimensional assessment, benchmarking and selection of paraphrase detection models. We find that paraphrase detection models under our fine-grained evaluation lens exhibit trade-offs that cannot be captured through a single classification dataset. Furthermore, PARAPHRASUS allows prompt calibration for different use cases, tailoring LLM models to specific strictness levels. PARAPHRASUS includes 3 challenges spanning over 10 datasets, including 8 repurposed and 2 newly annotated; we release it along with a benchmarking library at https://github.com/impresso/paraphrasus</abstract>
<identifier type="citekey">michail-etal-2025-paraphrasus</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.585/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8749</start>
<end>8762</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PARAPHRASUS: A Comprehensive Benchmark for Evaluating Paraphrase Detection Models
%A Michail, Andrianos
%A Clematide, Simon
%A Opitz, Juri
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F michail-etal-2025-paraphrasus
%X The task of determining whether two texts are paraphrases has long been a challenge in NLP. However, the prevailing notion of paraphrase is often quite simplistic, offering only a limited view of the vast spectrum of paraphrase phenomena. Indeed, we find that evaluating models in a paraphrase dataset can leave uncertainty about their true semantic understanding. To alleviate this, we create PARAPHRASUS, a benchmark designed for multi-dimensional assessment, benchmarking and selection of paraphrase detection models. We find that paraphrase detection models under our fine-grained evaluation lens exhibit trade-offs that cannot be captured through a single classification dataset. Furthermore, PARAPHRASUS allows prompt calibration for different use cases, tailoring LLM models to specific strictness levels. PARAPHRASUS includes 3 challenges spanning over 10 datasets, including 8 repurposed and 2 newly annotated; we release it along with a benchmarking library at https://github.com/impresso/paraphrasus
%U https://aclanthology.org/2025.coling-main.585/
%P 8749-8762
Markdown (Informal)
[PARAPHRASUS: A Comprehensive Benchmark for Evaluating Paraphrase Detection Models](https://aclanthology.org/2025.coling-main.585/) (Michail et al., COLING 2025)
ACL