# Generalists vs. Specialists: Evaluating Large Language Models for Urdu

arXiv: https://arxiv.org/abs/2407.04459 · HTML: https://mlsanity.com/paper/2407.04459/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 5 Jul 2024.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Systematic Inequalities in Language Technology Performance across the World's Languages](https://mlsanity.com/paper/2110.06733/) (2021)
- [MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks](https://mlsanity.com/paper/2311.07463/) (2023)
- [IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages](https://mlsanity.com/paper/2404.16816/) (2024)
- [GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP](https://mlsanity.com/paper/2305.14976/) (2023)
- [Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset](https://mlsanity.com/paper/2007.01176/) (2020)
- [Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility](https://mlsanity.com/paper/2305.10235/) (2023)
- [UQA: Corpus for Urdu Question Answering](https://mlsanity.com/paper/2405.01458/) (2024)
- [Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks](https://mlsanity.com/paper/2405.15453/) (2024)
- [Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021](https://mlsanity.com/paper/2207.06710/) (2022)

## Built on by (most cited first, 5 of 5)

- [Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges](https://mlsanity.com/paper/2509.11570/) (2025)
- [UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings](https://mlsanity.com/paper/2502.16961/) (2025)
- [Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models](https://mlsanity.com/paper/2503.21530/) (2025)
- [DunbaaBERT: From Sacrifice to Semantics](https://mlsanity.com/paper/2605.26935/) (2026)
- [Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO](https://mlsanity.com/paper/2412.12997/) (2024)

## Abstract (arXiv)

In this paper, we compare general-purpose models, GPT-4-Turbo and Llama-3-8b, with special-purpose models--XLM-Roberta-large, mT5-large, and Llama-3-8b--that have been fine-tuned on specific tasks. We focus on seven classification and seven generation tasks to evaluate the performance of these models on Urdu language. Urdu has 70 million native speakers, yet it remains underrepresented in Natural Language Processing (NLP). Despite the frequent advancements in Large Language Models (LLMs), their performance in low-resource languages, including Urdu, still needs to be explored. We also conduct a human evaluation for the generation tasks and compare the results with the evaluations performed by GPT-4-Turbo, Llama-3-8b and Claude 3.5 Sonnet. We find that special-purpose models consistently outperform general-purpose models across various tasks. We also find that the evaluation done by GPT-4-Turbo for generation tasks aligns more closely with human evaluation compared to the evaluation the evaluation done by Llama-3-8b. This paper contributes to the NLP community by providing insights into the effectiveness of general and specific-purpose LLMs for low-resource languages.