Enterprise Benchmarks for Large Language Model Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Bing, Takeuchi, Mikio, Kawahara, Ryo, Asthana, Shubhi, Hossain, Md. Maruf, Ren, Guang-Jie, Soule, Kate, Zhu, Yada
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917805952073728
author Zhang, Bing
Takeuchi, Mikio
Kawahara, Ryo
Asthana, Shubhi
Hossain, Md. Maruf
Ren, Guang-Jie
Soule, Kate
Zhu, Yada
author_facet Zhang, Bing
Takeuchi, Mikio
Kawahara, Ryo
Asthana, Shubhi
Hossain, Md. Maruf
Ren, Guang-Jie
Soule, Kate
Zhu, Yada
contents The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be able to benchmark enterprise datasets for various tasks. This work presents a systematic exploration of benchmarking strategies tailored to LLM evaluation, focusing on the utilization of domain-specific datasets and consisting of a variety of NLP tasks. The proposed evaluation framework encompasses 25 publicly available datasets from diverse enterprise domains like financial services, legal, cyber security, and climate and sustainability. The diverse performance of 13 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12857
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enterprise Benchmarks for Large Language Model Evaluation
Zhang, Bing
Takeuchi, Mikio
Kawahara, Ryo
Asthana, Shubhi
Hossain, Md. Maruf
Ren, Guang-Jie
Soule, Kate
Zhu, Yada
Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be able to benchmark enterprise datasets for various tasks. This work presents a systematic exploration of benchmarking strategies tailored to LLM evaluation, focusing on the utilization of domain-specific datasets and consisting of a variety of NLP tasks. The proposed evaluation framework encompasses 25 publicly available datasets from diverse enterprise domains like financial services, legal, cyber security, and climate and sustainability. The diverse performance of 13 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub.
title Enterprise Benchmarks for Large Language Model Evaluation
topic Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2410.12857