Portrait de Vivek Verma

Vivek Verma

Maîtrise professionnelle - UdeM
Co-supervisor
David Ifeoluwa Adelani
Sujets de recherche
Apprentissage profond
Grands modèles de langage (LLM)
IA digne de confiance
Modèles probabilistes
Traitement du langage naturel
Google Scholar
GitHub

Publications

mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks
Luel Hagos Beyene
Vivek Verma
Min Ma
Jesujoba Oluwadara Alabi
Fabian David Schmidt
Joyce Nakatumba-Nabende
David Ifeoluwa Adelani
Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as spe… (voir plus)ech. However, their evaluation is often limited to English and a few high-resource languages. For low-resource languages, there is no standardized evaluation benchmark. In this paper, we address this gap by introducing mSTEB, a new benchmark to evaluate the performance of LLMs on a wide range of tasks covering language identification, text classification, question answering, and translation tasks on both speech and text modalities. We evaluated the performance of leading LLMs such as Gemini 2.0 Flash and GPT-4o (Audio) and state-of-the-art open models such as Qwen 2 Audio and Gemma 3 27B. Our evaluation shows a wide gap in performance between high-resource and low-resource languages, especially for languages spoken in Africa and Americas/Oceania. Our findings show that more investment is needed to address their under-representation in LLMs coverage.
2025-06-10
ArXiv (prépublication)
arxiv.org
arxiv.org
mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks
Luel Hagos Beyene
Vivek Verma
Min Ma
Jesujoba Oluwadara Alabi
Fabian David Schmidt
Joyce Nakatumba-Nabende
David Ifeoluwa Adelani
Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as spe… (voir plus)ech. However, their evaluation is often limited to English and a few high-resource languages. For low-resource languages, there is no standardized evaluation benchmark. In this paper, we address this gap by introducing mSTEB, a new benchmark to evaluate the performance of LLMs on a wide range of tasks covering language identification, text classification, question answering, and translation tasks on both speech and text modalities. We evaluated the performance of leading LLMs such as Gemini 2.0 Flash and GPT-4o (Audio) and state-of-the-art open models such as Qwen 2 Audio and Gemma 3 27B. Our evaluation shows a wide gap in performance between high-resource and low-resource languages, especially for languages spoken in Africa and Americas/Oceania. Our findings show that more investment is needed to address their under-representation in LLMs coverage.
2025-06-10
ArXiv (prépublication)
doi.org
arxiv.org