Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Azam, Gulfarogh, Sadique, Mohd, Ali, Saif, Nadeem, Mohammad, Cambria, Erik, Sohail, Shahab Saquib, Alam, Mohammad Sultan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912395252727808
author Azam, Gulfarogh
Sadique, Mohd
Ali, Saif
Nadeem, Mohammad
Cambria, Erik
Sohail, Shahab Saquib
Alam, Mohammad Sultan
author_facet Azam, Gulfarogh
Sadique, Mohd
Ali, Saif
Nadeem, Mohammad
Cambria, Erik
Sohail, Shahab Saquib
Alam, Mohammad Sultan
contents Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse contexts such as India. Despite significant advancements through specialized models like IndicXlit, recent developments in large language models suggest a potential for general-purpose models to excel at this task without explicit task-specific training. The current work systematically evaluates the performance of prominent LLMs, including GPT-4o, GPT-4.5, GPT-4.1, Gemma-3-27B-it, and Mistral-Large against IndicXlit, a state-of-the-art transliteration model, across ten major Indian languages. Experiments utilized standard benchmarks, including Dakshina and Aksharantar datasets, with performance assessed via Top-1 Accuracy and Character Error Rate. Our findings reveal that while GPT family models generally outperform other LLMs and IndicXlit for most instances. Additionally, fine-tuning GPT-4o improves performance on specific languages notably. An extensive error analysis and robustness testing under noisy conditions further elucidate strengths of LLMs compared to specialized models, highlighting the efficacy of foundational models for a wide spectrum of specialized applications with minimal overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19851
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages
Azam, Gulfarogh
Sadique, Mohd
Ali, Saif
Nadeem, Mohammad
Cambria, Erik
Sohail, Shahab Saquib
Alam, Mohammad Sultan
Computation and Language
Artificial Intelligence
Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse contexts such as India. Despite significant advancements through specialized models like IndicXlit, recent developments in large language models suggest a potential for general-purpose models to excel at this task without explicit task-specific training. The current work systematically evaluates the performance of prominent LLMs, including GPT-4o, GPT-4.5, GPT-4.1, Gemma-3-27B-it, and Mistral-Large against IndicXlit, a state-of-the-art transliteration model, across ten major Indian languages. Experiments utilized standard benchmarks, including Dakshina and Aksharantar datasets, with performance assessed via Top-1 Accuracy and Character Error Rate. Our findings reveal that while GPT family models generally outperform other LLMs and IndicXlit for most instances. Additionally, fine-tuning GPT-4o improves performance on specific languages notably. An extensive error analysis and robustness testing under noisy conditions further elucidate strengths of LLMs compared to specialized models, highlighting the efficacy of foundational models for a wide spectrum of specialized applications with minimal overhead.
title Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.19851