Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.08727 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913313969930240 |
|---|---|
| author | Zhang, Xiang Khedri, Khatoon Rawassizadeh, Reza |
| author_facet | Zhang, Xiang Khedri, Khatoon Rawassizadeh, Reza |
| contents | Large Language Models (LLMs) can automate or substitute different types of tasks in the software engineering process. This study evaluates the resource utilization and accuracy of LLM in interpreting and executing natural language queries against traditional SQL within relational database management systems. We empirically examine the resource utilization and accuracy of nine LLMs varying from 7 to 34 Billion parameters, including Llama2 7B, Llama2 13B, Mistral, Mixtral, Optimus-7B, SUS-chat-34B, platypus-yi-34b, NeuralHermes-2.5-Mistral-7B and Starling-LM-7B-alpha, using a small transaction dataset. Our findings indicate that using LLMs for database queries incurs significant energy overhead (even small and quantized models), making it an environmentally unfriendly approach. Therefore, we advise against replacing relational databases with LLMs due to their substantial resource utilization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08727 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can LLMs substitute SQL? Comparing Resource Utilization of Querying LLMs versus Traditional Relational Databases Zhang, Xiang Khedri, Khatoon Rawassizadeh, Reza Databases Artificial Intelligence Computation and Language 68-04 H.2.m Large Language Models (LLMs) can automate or substitute different types of tasks in the software engineering process. This study evaluates the resource utilization and accuracy of LLM in interpreting and executing natural language queries against traditional SQL within relational database management systems. We empirically examine the resource utilization and accuracy of nine LLMs varying from 7 to 34 Billion parameters, including Llama2 7B, Llama2 13B, Mistral, Mixtral, Optimus-7B, SUS-chat-34B, platypus-yi-34b, NeuralHermes-2.5-Mistral-7B and Starling-LM-7B-alpha, using a small transaction dataset. Our findings indicate that using LLMs for database queries incurs significant energy overhead (even small and quantized models), making it an environmentally unfriendly approach. Therefore, we advise against replacing relational databases with LLMs due to their substantial resource utilization. |
| title | Can LLMs substitute SQL? Comparing Resource Utilization of Querying LLMs versus Traditional Relational Databases |
| topic | Databases Artificial Intelligence Computation and Language 68-04 H.2.m |
| url | https://arxiv.org/abs/2404.08727 |