@unpublished{wang2024gorilla,
author = {Wang, Xin},
title = {Gorilla: Teaching LLMs to Use Tools},
year = {2024},
month = {October},
abstract = {Large Language Models (LLMs) have seen an im-pressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. How-ever, their potential to effectively use tools via API calls remains unfulfilled. This is a challenging task even for today’s state-of- the-art LLMs such as GPT-4 largely due to their unawareness of what APIs are available and how to use them in a frequently updated toolset. We develop Gorilla, a finetuned LLaMA model that surpasses the performance of GPT-4 on writing API calls. When combined with a document retriever, Gorilla demonstrates a strong capability to adapt to test-time document changes, enabling flexible user updates or version changes. It also substantially mitigates the issue of hallucination, commonly encountered when prompting LLMs directly. To evaluate the model’s ability, we introduce APIBench, a comprehensive dataset consisting of HuggingFace, TorchHub, and TensorHubAPIs. The successful integration of the retrieval system with Gorilla demonstrates the potential for LLMs to use tools more accurately, keep up with frequently updated documentation, and consequently increase the reliability and applicability of their outputs. Gorilla’s code, model, and data will be open-sourced.},
url = {http://approjects.co.za/?big=en-us/research/publication/gorilla-teaching-llms-to-use-tools/},
}