<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tahir-etal-2025-benchmarking">
    <titleInfo>
        <title>Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Munief</namePart>
        <namePart type="given">Hassan</namePart>
        <namePart type="family">Tahir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sana</namePart>
        <namePart type="family">Shams</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Layba</namePart>
        <namePart type="family">Fiaz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Farah</namePart>
        <namePart type="family">Adeeba</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sarmad</namePart>
        <namePart type="family">Hussain</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 First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kengatharaiyer</namePart>
            <namePart type="family">Sarveswaran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ashwini</namePart>
            <namePart type="family">Vaidya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bal</namePart>
            <namePart type="family">Krishna Bal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sana</namePart>
            <namePart type="family">Shams</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Surendrabikram</namePart>
            <namePart type="family">Thapa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large Language Models (LLMs) pre-trained on multilingual data have revolutionized natural language processing research, by transitioning from languages and task specific model pipelines to a single model adapted on a variety of tasks. However majority of existing multilingual NLP benchmarks for LLMs provide evaluation data in only few languages with little linguistic diversity. In addition these benchmarks lack quality assessment against the respective state-of the art models. This study presents an in-depth examination of 7 prominent LLMs: GPT-3.5-turbo, Llama 2-7B-Chat, Llama 3.1-8B, Bloomz 3B, Bloomz 7B1, Ministral-8B and Whisper (Large, medium and small variant) across 17 tasks using 22 datasets, 13.8 hours of speech, in a zero-shot setting, and their performance against state-of-the-art (SOTA) models, has been compared and analyzed. Our experiments show that SOTA models currently outperform encoder-decoder models in majority of Urdu NLP tasks under zero-shot settings. However, comparing Llama 3.1-8B over prior version Llama 2-7B-Chat, we can deduce that with improved language coverage, LLMs can surpass these SOTA models. Our results emphasize that models with fewer parameters but richer language-specific data, like Llama 3.1-8B, often outperform larger models with lower language diversity, such as GPT-3.5, in several tasks.</abstract>
    <identifier type="citekey">tahir-etal-2025-benchmarking</identifier>
    <location>
        <url>https://aclanthology.org/2025.chipsal-1.3/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>17</start>
            <end>34</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks
%A Tahir, Munief Hassan
%A Shams, Sana
%A Fiaz, Layba
%A Adeeba, Farah
%A Hussain, Sarmad
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%Y Krishna Bal, Bal
%Y Shams, Sana
%Y Thapa, Surendrabikram
%S Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F tahir-etal-2025-benchmarking
%X Large Language Models (LLMs) pre-trained on multilingual data have revolutionized natural language processing research, by transitioning from languages and task specific model pipelines to a single model adapted on a variety of tasks. However majority of existing multilingual NLP benchmarks for LLMs provide evaluation data in only few languages with little linguistic diversity. In addition these benchmarks lack quality assessment against the respective state-of the art models. This study presents an in-depth examination of 7 prominent LLMs: GPT-3.5-turbo, Llama 2-7B-Chat, Llama 3.1-8B, Bloomz 3B, Bloomz 7B1, Ministral-8B and Whisper (Large, medium and small variant) across 17 tasks using 22 datasets, 13.8 hours of speech, in a zero-shot setting, and their performance against state-of-the-art (SOTA) models, has been compared and analyzed. Our experiments show that SOTA models currently outperform encoder-decoder models in majority of Urdu NLP tasks under zero-shot settings. However, comparing Llama 3.1-8B over prior version Llama 2-7B-Chat, we can deduce that with improved language coverage, LLMs can surpass these SOTA models. Our results emphasize that models with fewer parameters but richer language-specific data, like Llama 3.1-8B, often outperform larger models with lower language diversity, such as GPT-3.5, in several tasks.
%U https://aclanthology.org/2025.chipsal-1.3/
%P 17-34

Markdown (Informal)

[Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks](https://aclanthology.org/2025.chipsal-1.3/) (Tahir et al., CHiPSAL 2025)

• Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks (Tahir et al., CHiPSAL 2025)

ACL

• Munief Hassan Tahir, Sana Shams, Layba Fiaz, Farah Adeeba, and Sarmad Hussain. 2025. Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks. In Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025), pages 17–34, Abu Dhabi, UAE. International Committee on Computational Linguistics.