Gorilla: Large Language Model Connected with Massive APIs

TL;DR

Gorilla is a fine-tuned LLaMA-based model that significantly improves API call accuracy over GPT-4, effectively uses document retrieval for dynamic updates, and reduces hallucinations in tool usage.

Contribution

The paper introduces Gorilla, a novel fine-tuned LLaMA model that outperforms GPT-4 in API call generation and demonstrates enhanced adaptability and reliability through integration with a retrieval system.

Findings

Gorilla surpasses GPT-4 in API call accuracy.

Integration with retrieval improves adaptability to document changes.

Reduces hallucinations in API usage compared to prompting GPT-4.

Abstract

Large Language Models (LLMs) have seen an impressive wave of advances recently, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. However, 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 inability to generate accurate input arguments and their tendency to hallucinate the wrong usage of an API call. We release Gorilla, a finetuned LLaMA-based 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 TensorHub APIs. 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, data, and demo are available at https://gorilla.cs.berkeley.edu