让手机上的大模型精准调用外部功能，还防遗忘。
Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs
- 用逻辑生成高质量训练数据，提升函数调用准确率。
- 在多个任务上函数调用准确率显著提升，遗忘问题大幅缓解。
- 适合想在手机端部署智能助手的研究者和开发者。
大语言模型（LLMs）在移动端的集成日益普遍，使其能够调用外部API以增强性能。然而，数据稀缺、问题格式无效及灾难性遗忘等问题制约了本地化LLM代理的发展。为此，我们提出Alopex框架，利用Fox LLM实现精确的本地函数调用。Alopex引入基于逻辑的高质量训练数据生成方法，并采用新颖的“描述-问题-输出”格式进行微调，降低函数信息泄露风险。此外，通过数据混合策略，将函数调用数据与教材数据结合，缓解灾难性遗忘。实验表明，Alopex显著提升了函数调用准确率并有效减少遗忘，为无需人工干预的函数调用能力集成提供了可靠方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。