LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dalvi, Fahim, Hasanain, Maram, Boughorbel, Sabri, Mousi, Basel, Abdaljalil, Samir, Nazar, Nizi, Abdelali, Ahmed, Chowdhury, Shammur Absar, Mubarak, Hamdy, Ali, Ahmed, Hawasly, Majd, Durrani, Nadir, Alam, Firoj
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914690935816192
author Dalvi, Fahim
Hasanain, Maram
Boughorbel, Sabri
Mousi, Basel
Abdaljalil, Samir
Nazar, Nizi
Abdelali, Ahmed
Chowdhury, Shammur Absar
Mubarak, Hamdy
Ali, Ahmed
Hawasly, Majd
Durrani, Nadir
Alam, Firoj
author_facet Dalvi, Fahim
Hasanain, Maram
Boughorbel, Sabri
Mousi, Basel
Abdaljalil, Samir
Nazar, Nizi
Abdelali, Ahmed
Chowdhury, Shammur Absar
Mubarak, Hamdy
Ali, Ahmed
Hawasly, Majd
Durrani, Nadir
Alam, Firoj
contents The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework, which can be seamlessly customized to evaluate LLMs for any NLP task, regardless of language. The framework features generic dataset loaders, several model providers, and pre-implements most standard evaluation metrics. It supports in-context learning with zero- and few-shot settings. A specific dataset and task can be evaluated for a given LLM in less than 20 lines of code while allowing full flexibility to extend the framework for custom datasets, models, or tasks. The framework has been tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We open-sourced LLMeBench for the community (https://github.com/qcri/LLMeBench/) and a video demonstrating the framework is available online. (https://youtu.be/9cC2m_abk3A)
format Preprint
id arxiv_https___arxiv_org_abs_2308_04945
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
Dalvi, Fahim
Hasanain, Maram
Boughorbel, Sabri
Mousi, Basel
Abdaljalil, Samir
Nazar, Nizi
Abdelali, Ahmed
Chowdhury, Shammur Absar
Mubarak, Hamdy
Ali, Ahmed
Hawasly, Majd
Durrani, Nadir
Alam, Firoj
Computation and Language
Artificial Intelligence
68T50
F.2.2; I.2.7
The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework, which can be seamlessly customized to evaluate LLMs for any NLP task, regardless of language. The framework features generic dataset loaders, several model providers, and pre-implements most standard evaluation metrics. It supports in-context learning with zero- and few-shot settings. A specific dataset and task can be evaluated for a given LLM in less than 20 lines of code while allowing full flexibility to extend the framework for custom datasets, models, or tasks. The framework has been tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We open-sourced LLMeBench for the community (https://github.com/qcri/LLMeBench/) and a video demonstrating the framework is available online. (https://youtu.be/9cC2m_abk3A)
title LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
topic Computation and Language
Artificial Intelligence
68T50
F.2.2; I.2.7
url https://arxiv.org/abs/2308.04945