<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmed-2026-chain">
    <titleInfo>
        <title>Chain-of-Thought in a Low-Resource Language: A Factorial Study of Exemplar and Reasoning Language Effects in Urdu</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ateeb</namePart>
        <namePart type="family">Ahmed</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>The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Leonardo</namePart>
            <namePart type="family">Ranaldi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Giulia</namePart>
            <namePart type="family">Pucci</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Federico</namePart>
            <namePart type="family">Ranaldi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="family">Valentino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexandra</namePart>
            <namePart type="family">Birch</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabio</namePart>
            <namePart type="given">Massimo</namePart>
            <namePart type="family">Zanzotto</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">979-8-89176-483-5</identifier>
    </relatedItem>
    <abstract>Chain-of-thought (CoT) prompting has been shown theoretically to extend the computational capacity of transformers by providing intermediate reasoning steps (Feng et al., 2023; Amiri et al., 2025). Whether these benefits carry over to low-resource languages is not well understood, and Urdu in particular has received very little attention in this context. We investigate two prompt factors (the language of few-shot exemplars and the language of the reasoning chain) using a 2 × 2 factorial design on MGSM Urdu and Math-500 Urdu, evaluated with Gemini 2.5 Flash. We find a significant interaction between exemplar and CoT language (item-level logistic regression, z = 6.9, p \ensuremath&lt; 0.001): switching to Urdu CoT with English exemplars causes a 34.8 percentage point accuracy drop on MGSM, while the same switch with Urdu exemplars results in only a 1.6 point drop. We also find that Urdu CoT produces longer token sequences than English CoT (139 vs. 101 tokens on average) but not correspondingly more discrete reasoning steps: a script-aware, manually validated step count shows Urdu CoT yields slightly fewer discrete steps (2.5 vs. 3.0 on average), with the reduction concentrated in the mismatchedexemplar condition, indicating that added verbosity does not translate into added reasoning structure. Chain length correlates positively with accuracy (r = 0.42, p \ensuremath&lt; 0.001), consistent with the theoretical framework. The main takeaway is that exemplar language is a critical moderator of CoT effectiveness in Urdu.</abstract>
    <identifier type="citekey">ahmed-2026-chain</identifier>
    <location>
        <url>https://aclanthology.org/2026.oracle-main.5/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>75</start>
            <end>83</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Chain-of-Thought in a Low-Resource Language: A Factorial Study of Exemplar and Reasoning Language Effects in Urdu
%A Ahmed, Ateeb
%Y Ranaldi, Leonardo
%Y Pucci, Giulia
%Y Ranaldi, Federico
%Y Valentino, Marco
%Y Birch, Alexandra
%Y Zanzotto, Fabio Massimo
%S The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-483-5
%F ahmed-2026-chain
%X Chain-of-thought (CoT) prompting has been shown theoretically to extend the computational capacity of transformers by providing intermediate reasoning steps (Feng et al., 2023; Amiri et al., 2025). Whether these benefits carry over to low-resource languages is not well understood, and Urdu in particular has received very little attention in this context. We investigate two prompt factors (the language of few-shot exemplars and the language of the reasoning chain) using a 2 × 2 factorial design on MGSM Urdu and Math-500 Urdu, evaluated with Gemini 2.5 Flash. We find a significant interaction between exemplar and CoT language (item-level logistic regression, z = 6.9, p \ensuremath< 0.001): switching to Urdu CoT with English exemplars causes a 34.8 percentage point accuracy drop on MGSM, while the same switch with Urdu exemplars results in only a 1.6 point drop. We also find that Urdu CoT produces longer token sequences than English CoT (139 vs. 101 tokens on average) but not correspondingly more discrete reasoning steps: a script-aware, manually validated step count shows Urdu CoT yields slightly fewer discrete steps (2.5 vs. 3.0 on average), with the reduction concentrated in the mismatchedexemplar condition, indicating that added verbosity does not translate into added reasoning structure. Chain length correlates positively with accuracy (r = 0.42, p \ensuremath< 0.001), consistent with the theoretical framework. The main takeaway is that exemplar language is a critical moderator of CoT effectiveness in Urdu.
%U https://aclanthology.org/2026.oracle-main.5/
%P 75-83

Markdown (Informal)

[Chain-of-Thought in a Low-Resource Language: A Factorial Study of Exemplar and Reasoning Language Effects in Urdu](https://aclanthology.org/2026.oracle-main.5/) (Ahmed, ORACLE 2026)

• Chain-of-Thought in a Low-Resource Language: A Factorial Study of Exemplar and Reasoning Language Effects in Urdu (Ahmed, ORACLE 2026)

ACL

• Ateeb Ahmed. 2026. Chain-of-Thought in a Low-Resource Language: A Factorial Study of Exemplar and Reasoning Language Effects in Urdu. In The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE), pages 75–83, Budapest, Hungary. Association for Computational Linguistics.