Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ran, Yide, Xu, Zhaozhuo, Yao, Yuhang, Hu, Zijian, Han, Shanshan, Jin, Han, Shah, Alay Dilipbhai, Zhang, Jipeng, Stripelis, Dimitris, Zhang, Tong, Avestimehr, Salman, He, Chaoyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916473232949248
author Ran, Yide
Xu, Zhaozhuo
Yao, Yuhang
Hu, Zijian
Han, Shanshan
Jin, Han
Shah, Alay Dilipbhai
Zhang, Jipeng
Stripelis, Dimitris
Zhang, Tong
Avestimehr, Salman
He, Chaoyang
author_facet Ran, Yide
Xu, Zhaozhuo
Yao, Yuhang
Hu, Zijian
Han, Shanshan
Jin, Han
Shah, Alay Dilipbhai
Zhang, Jipeng
Stripelis, Dimitris
Zhang, Tong
Avestimehr, Salman
He, Chaoyang
contents The rapid advancement of Large Language Models (LLMs) has led to their increased integration into mobile devices for personalized assistance, which enables LLMs to call external API functions to enhance their performance. However, challenges such as data scarcity, ineffective question formatting, and catastrophic forgetting hinder the development of on-device LLM agents. To tackle these issues, we propose Alopex, a framework that enables precise on-device function calls using the Fox LLM. Alopex introduces a logic-based method for generating high-quality training data and a novel ``description-question-output'' format for fine-tuning, reducing risks of function information leakage. Additionally, a data mixing strategy is used to mitigate catastrophic forgetting, combining function call data with textbook datasets to enhance performance in various tasks. Experimental results show that Alopex improves function call accuracy and significantly reduces catastrophic forgetting, providing a robust solution for integrating function call capabilities into LLMs without manual intervention.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05209
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs
Ran, Yide
Xu, Zhaozhuo
Yao, Yuhang
Hu, Zijian
Han, Shanshan
Jin, Han
Shah, Alay Dilipbhai
Zhang, Jipeng
Stripelis, Dimitris
Zhang, Tong
Avestimehr, Salman
He, Chaoyang
Artificial Intelligence
Computation and Language
The rapid advancement of Large Language Models (LLMs) has led to their increased integration into mobile devices for personalized assistance, which enables LLMs to call external API functions to enhance their performance. However, challenges such as data scarcity, ineffective question formatting, and catastrophic forgetting hinder the development of on-device LLM agents. To tackle these issues, we propose Alopex, a framework that enables precise on-device function calls using the Fox LLM. Alopex introduces a logic-based method for generating high-quality training data and a novel ``description-question-output'' format for fine-tuning, reducing risks of function information leakage. Additionally, a data mixing strategy is used to mitigate catastrophic forgetting, combining function call data with textbook datasets to enhance performance in various tasks. Experimental results show that Alopex improves function call accuracy and significantly reduces catastrophic forgetting, providing a robust solution for integrating function call capabilities into LLMs without manual intervention.
title Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2411.05209