Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!
Add to Chrome
Add to Firefox
Add to EdgeGeckOpt: LLM System Efficiency via Intent-Based Tool Selection
Apr 24, 2024
In this preliminary study, we investigate a GPT-driven intent-based reasoning approach to streamline tool selection for large language models (LLMs) aimed at system efficiency. By identifying the intent behind user prompts at runtime, we narrow down the API toolset required for task execution, reducing token consumption by up to 24.6\%. Early results on a real-world, massively parallel Copilot platform with over 100 GPT-4-Turbo nodes show cost reductions and potential towards improving LLM-based system efficiency.
* GLSVLSI 2024
View paper on