@inproceedings{nacar-etal-2026-arascholar,
title = "{A}ra{S}cholar: Calibrating Academic Paraphrasing in {M}odern {S}tandard {A}rabic",
author = "Nacar, Omer and
Al Wazrah, Asma and
Almatham, Rawan Nasser and
Altamimi, Afrah and
Alosaimy, Abdulrahman",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.24/",
pages = "340--355",
ISBN = "979-8-89176-473-6",
abstract = "Academic paraphrasing in Modern Standard Arabic must change expression without distorting scientific content. We study this balance through AraScholar, a corpus of 20,002 manually written source{--}paraphrase pairs with 522 raw domain labels and item-level provenance. On 2,000 held-out sentences, fine-tuned AraT5v2 favors lexical reuse under beam search, while frontier models produce more extensive rewrites. With corrected Arabic punctuation normalization, diverse decoding and preservation-constrained reranking attain 74.25{\%} coverage of a fixed novelty{--}preservation band, compared with 52.60{\%} for zero-shot GPT-4o. Gold coverage is only 46.65{\%}, showing that this band measures constraint compliance rather than human quality. Post-hoc target matching substantially improves a calibrated GPT-4o control and narrows the gap, although candidate budgets differ. Crucially, an independent 200-instance audit favors frontier models on meaning and paraphrase quality. We document the corpus, decoding controls, negative distillation result, and metric sensitivity, including test-derived calibration and checkpoint-selection limitations. The findings establish operating-point control as a useful capability while demonstrating why calibration must be evaluated alongside independent assessments of writing quality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nacar-etal-2026-arascholar">
<titleInfo>
<title>AraScholar: Calibrating Academic Paraphrasing in Modern Standard Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Al Wazrah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="given">Nasser</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afrah</namePart>
<namePart type="family">Altamimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Alosaimy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</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">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>Academic paraphrasing in Modern Standard Arabic must change expression without distorting scientific content. We study this balance through AraScholar, a corpus of 20,002 manually written source–paraphrase pairs with 522 raw domain labels and item-level provenance. On 2,000 held-out sentences, fine-tuned AraT5v2 favors lexical reuse under beam search, while frontier models produce more extensive rewrites. With corrected Arabic punctuation normalization, diverse decoding and preservation-constrained reranking attain 74.25% coverage of a fixed novelty–preservation band, compared with 52.60% for zero-shot GPT-4o. Gold coverage is only 46.65%, showing that this band measures constraint compliance rather than human quality. Post-hoc target matching substantially improves a calibrated GPT-4o control and narrows the gap, although candidate budgets differ. Crucially, an independent 200-instance audit favors frontier models on meaning and paraphrase quality. We document the corpus, decoding controls, negative distillation result, and metric sensitivity, including test-derived calibration and checkpoint-selection limitations. The findings establish operating-point control as a useful capability while demonstrating why calibration must be evaluated alongside independent assessments of writing quality.</abstract>
<identifier type="citekey">nacar-etal-2026-arascholar</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.24/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>340</start>
<end>355</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AraScholar: Calibrating Academic Paraphrasing in Modern Standard Arabic
%A Nacar, Omer
%A Al Wazrah, Asma
%A Almatham, Rawan Nasser
%A Altamimi, Afrah
%A Alosaimy, Abdulrahman
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F nacar-etal-2026-arascholar
%X Academic paraphrasing in Modern Standard Arabic must change expression without distorting scientific content. We study this balance through AraScholar, a corpus of 20,002 manually written source–paraphrase pairs with 522 raw domain labels and item-level provenance. On 2,000 held-out sentences, fine-tuned AraT5v2 favors lexical reuse under beam search, while frontier models produce more extensive rewrites. With corrected Arabic punctuation normalization, diverse decoding and preservation-constrained reranking attain 74.25% coverage of a fixed novelty–preservation band, compared with 52.60% for zero-shot GPT-4o. Gold coverage is only 46.65%, showing that this band measures constraint compliance rather than human quality. Post-hoc target matching substantially improves a calibrated GPT-4o control and narrows the gap, although candidate budgets differ. Crucially, an independent 200-instance audit favors frontier models on meaning and paraphrase quality. We document the corpus, decoding controls, negative distillation result, and metric sensitivity, including test-derived calibration and checkpoint-selection limitations. The findings establish operating-point control as a useful capability while demonstrating why calibration must be evaluated alongside independent assessments of writing quality.
%U https://aclanthology.org/2026.arabicnlp-main.24/
%P 340-355
Markdown (Informal)
[AraScholar: Calibrating Academic Paraphrasing in Modern Standard Arabic](https://aclanthology.org/2026.arabicnlp-main.24/) (Nacar et al., ArabicNLP 2026)
ACL