@inproceedings{dahou-cheragui-2026-helpful,
title = "Helpful or Harmful? The Dual Role of Linguistic Features in {LLM}-Based Dialectal Machine Translation",
author = "Dahou, Abdelhalim Hafedh and
Cheragui, Mohamed Amine",
editor = "Al-Khalifa, Hend and
El-Haj, Mo and
Ezzini, Saad",
booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.osact-1.8/",
doi = "10.63317/5dpmbr8bbedw",
pages = "66--75",
abstract = "Large Language Models (LLMs) have shown promising results in dialectal machine translation, yet the impact of explicit linguistic features remains underexplored. This paper examines whether part-of-speech (POS) tags and diacritization help or hinder LLM-based translation between Algerian dialect (Darija) and Modern Standard Arabic (MSA). Using a linguistically enriched subset of the PADIC dataset, we conduct bidirectional experiments across several frontier and open-weight LLMs, evaluated with automatic metrics and human judgments of adequacy and fluency. Results reveal a dual and asymmetric effect: diacritics can improve adequacy in the MSA {\textrightarrow} Algerian dialect direction, while POS tags and forced diacritization often introduce noise, especially for Algerian dialect {\textrightarrow} MSA translation. We further observe a mismatch between traditional overlap-based metrics and human evaluation, suggesting limitations in current evaluation practices. Overall, explicit linguistic augmentation does not consistently benefit LLM-based dialectal translation and must be applied cautiously."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dahou-cheragui-2026-helpful">
<titleInfo>
<title>Helpful or Harmful? The Dual Role of Linguistic Features in LLM-Based Dialectal Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelhalim</namePart>
<namePart type="given">Hafedh</namePart>
<namePart type="family">Dahou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Amine</namePart>
<namePart type="family">Cheragui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
</titleInfo>
<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">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have shown promising results in dialectal machine translation, yet the impact of explicit linguistic features remains underexplored. This paper examines whether part-of-speech (POS) tags and diacritization help or hinder LLM-based translation between Algerian dialect (Darija) and Modern Standard Arabic (MSA). Using a linguistically enriched subset of the PADIC dataset, we conduct bidirectional experiments across several frontier and open-weight LLMs, evaluated with automatic metrics and human judgments of adequacy and fluency. Results reveal a dual and asymmetric effect: diacritics can improve adequacy in the MSA → Algerian dialect direction, while POS tags and forced diacritization often introduce noise, especially for Algerian dialect → MSA translation. We further observe a mismatch between traditional overlap-based metrics and human evaluation, suggesting limitations in current evaluation practices. Overall, explicit linguistic augmentation does not consistently benefit LLM-based dialectal translation and must be applied cautiously.</abstract>
<identifier type="citekey">dahou-cheragui-2026-helpful</identifier>
<identifier type="doi">10.63317/5dpmbr8bbedw</identifier>
<location>
<url>https://aclanthology.org/2026.osact-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>66</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Helpful or Harmful? The Dual Role of Linguistic Features in LLM-Based Dialectal Machine Translation
%A Dahou, Abdelhalim Hafedh
%A Cheragui, Mohamed Amine
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F dahou-cheragui-2026-helpful
%X Large Language Models (LLMs) have shown promising results in dialectal machine translation, yet the impact of explicit linguistic features remains underexplored. This paper examines whether part-of-speech (POS) tags and diacritization help or hinder LLM-based translation between Algerian dialect (Darija) and Modern Standard Arabic (MSA). Using a linguistically enriched subset of the PADIC dataset, we conduct bidirectional experiments across several frontier and open-weight LLMs, evaluated with automatic metrics and human judgments of adequacy and fluency. Results reveal a dual and asymmetric effect: diacritics can improve adequacy in the MSA → Algerian dialect direction, while POS tags and forced diacritization often introduce noise, especially for Algerian dialect → MSA translation. We further observe a mismatch between traditional overlap-based metrics and human evaluation, suggesting limitations in current evaluation practices. Overall, explicit linguistic augmentation does not consistently benefit LLM-based dialectal translation and must be applied cautiously.
%R 10.63317/5dpmbr8bbedw
%U https://aclanthology.org/2026.osact-1.8/
%U https://doi.org/10.63317/5dpmbr8bbedw
%P 66-75
Markdown (Informal)
[Helpful or Harmful? The Dual Role of Linguistic Features in LLM-Based Dialectal Machine Translation](https://aclanthology.org/2026.osact-1.8/) (Dahou & Cheragui, OSACT 2026)
ACL