@inproceedings{chaudhuri-etal-2026-hashtag,
title = "Hashtag {AI} at {H}allu{S}coring-2026: Distilling Knowledge-Graph Retrieval into Gemma 4 for {A}rabic Hallucination Detection",
author = "Chaudhuri, Anupam and
Simmons, Anj and
Mukherjee, Satwik and
Song, Rongrong",
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: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.138/",
pages = "1120--1125",
ISBN = "979-8-89176-497-2",
abstract = "We describe our submission to HalluScoring 2026 for Arabic hallucination detection in general-culture and Islamic-knowledge question answering. Our system adapts the instruction-tuned 12B-parameter Gemma 4 model with QLoRA. Its central idea is to use the Hashtag AI knowledge-graph retrieval system only during offline data construction: we query facts related to development-set failures, create contrastive training examples, and distill them into the model parameters. The submitted model is closed-book and uses no retrieval, search, or external knowledge at evaluation time. On organizer-provided test annotations, it obtains 73.59 macro-F1 on the 400-example Islamic set and 77.56 on the 1,600-example mixed-domain set; answer-option accuracies are 75.25{\%} and 81.13{\%}. Analysis shows strong science performance but lower recall for subtle hallucinations in history, geography, and Islamic knowledge."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaudhuri-etal-2026-hashtag">
<titleInfo>
<title>Hashtag AI at HalluScoring-2026: Distilling Knowledge-Graph Retrieval into Gemma 4 for Arabic Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anupam</namePart>
<namePart type="family">Chaudhuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anj</namePart>
<namePart type="family">Simmons</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satwik</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongrong</namePart>
<namePart type="family">Song</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: Shared Tasks</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">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>We describe our submission to HalluScoring 2026 for Arabic hallucination detection in general-culture and Islamic-knowledge question answering. Our system adapts the instruction-tuned 12B-parameter Gemma 4 model with QLoRA. Its central idea is to use the Hashtag AI knowledge-graph retrieval system only during offline data construction: we query facts related to development-set failures, create contrastive training examples, and distill them into the model parameters. The submitted model is closed-book and uses no retrieval, search, or external knowledge at evaluation time. On organizer-provided test annotations, it obtains 73.59 macro-F1 on the 400-example Islamic set and 77.56 on the 1,600-example mixed-domain set; answer-option accuracies are 75.25% and 81.13%. Analysis shows strong science performance but lower recall for subtle hallucinations in history, geography, and Islamic knowledge.</abstract>
<identifier type="citekey">chaudhuri-etal-2026-hashtag</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.138/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1120</start>
<end>1125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hashtag AI at HalluScoring-2026: Distilling Knowledge-Graph Retrieval into Gemma 4 for Arabic Hallucination Detection
%A Chaudhuri, Anupam
%A Simmons, Anj
%A Mukherjee, Satwik
%A Song, Rongrong
%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: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F chaudhuri-etal-2026-hashtag
%X We describe our submission to HalluScoring 2026 for Arabic hallucination detection in general-culture and Islamic-knowledge question answering. Our system adapts the instruction-tuned 12B-parameter Gemma 4 model with QLoRA. Its central idea is to use the Hashtag AI knowledge-graph retrieval system only during offline data construction: we query facts related to development-set failures, create contrastive training examples, and distill them into the model parameters. The submitted model is closed-book and uses no retrieval, search, or external knowledge at evaluation time. On organizer-provided test annotations, it obtains 73.59 macro-F1 on the 400-example Islamic set and 77.56 on the 1,600-example mixed-domain set; answer-option accuracies are 75.25% and 81.13%. Analysis shows strong science performance but lower recall for subtle hallucinations in history, geography, and Islamic knowledge.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.138/
%P 1120-1125
Markdown (Informal)
[Hashtag AI at HalluScoring-2026: Distilling Knowledge-Graph Retrieval into Gemma 4 for Arabic Hallucination Detection](https://aclanthology.org/2026.arabicnlp-sharedtasks.138/) (Chaudhuri et al., ArabicNLP 2026)
ACL