Large Language Models (LLMs) have made significant advancements in various tasks, such as mathematical reasoning and program synthesis. However, their ability to effectively use tools via API calls remains a challenge. Even state-of-the-art LLMs like GPT-4 struggle with generating accurate input arguments and often hallucinate incorrect API call usage. To address this issue, the researchers introduce Gorilla, a finetuned LLaMA-based model that outperforms GPT-4 in writing API calls. Gorilla demonstrates strong adaptability to test-time document changes when combined with a document retriever. This enables flexible user updates or version changes and mitigates the problem of hallucination commonly encountered when directly prompting LLMs. To evaluate Gorilla's performance, the researchers introduce APIBench, a comprehensive dataset consisting of HuggingFace, TorchHub, and TensorHub APIs. The successful integration of the retrieval system with Gorilla showcases the potential for LLMs to accurately use tools, keep up with frequently updated documentation, and improve the reliability and applicability of their outputs. The availability of Gorilla's code, model, data, and demo at https://gorilla.cs.berkeley.edu further facilitates its adoption. The paper also highlights the importance of empowering LLMs to use tools for accessing larger and changing knowledge bases and accomplishing complex computational tasks. By integrating plugins that allow LLMs to invoke external tools through APIs, they can become primary interfaces to computing infrastructure and the web. Techniques like Gorilla enhance an LLM's ability to identify appropriate APIs for specific tasks; correct usage of APIs improves an LLM's interaction with tools in various domains. The proposed pipeline for finetuning LLMs to call APIs surpasses GPT-4's performance in massive datasets collected by the researchers from companies like Samsung SDS, Uber, and VMware. Overall, these advancements contribute to expanding the capabilities of LLMs and their potential to revolutionize various industries by providing them with powerful interfaces that enable them to access large knowledge bases quickly while remaining reliable even when faced with frequent updates or version changes.
- Large Language Models (LLMs) have made significant advancements in various tasks
- LLMs struggle with generating accurate input arguments and often hallucinate incorrect API call usage
- Gorilla is a finetuned LLaMA-based model that outperforms GPT-4 in writing API calls
- Gorilla demonstrates strong adaptability to test-time document changes when combined with a document retriever
- Evaluation of Gorilla's performance is done using the APIBench dataset consisting of HuggingFace, TorchHub, and TensorHub APIs
- Successful integration of the retrieval system with Gorilla improves the reliability and applicability of LLM outputs
- Availability of Gorilla's code, model, data, and demo at https://gorilla.cs.berkeley.edu facilitates its adoption
- Empowering LLMs to use tools through APIs enhances their capabilities and interaction with tools in various domains
- The proposed pipeline for finetuning LLMs to call APIs surpasses GPT-4's performance in massive datasets collected from companies like Samsung SDS, Uber, and VMware
Large Language Models (LLMs) are advanced computer programs that can do many different tasks.
Generating accurate input arguments means coming up with the right information to use in a task.
API call usage refers to how LLMs use certain tools or programs to complete tasks.
Gorilla is a special type of LLM that is really good at writing API calls and is even better than GPT-4, another advanced program.
A document retriever helps Gorilla adapt to changes in documents it uses for tasks.
Evaluation means testing how well Gorilla works using a dataset of different APIs from companies like HuggingFace, TorchHub, and TensorHub.
Reliability means how trustworthy or dependable something is. The retrieval system makes LLM outputs more reliable and useful.
Applicability means how well something can be used in different situations. The retrieval system makes LLM outputs more applicable in different domains or areas.
Adoption means when people start using something new. Having Gorilla's code, model, data, and demo available makes it easier for people to start using it.
Finetuning LLMs means making them even better by using lots of data collected from companies like Samsung SDS, Uber, and VMware."
Large Language Models (LLMs) and Their Ability to Use Tools via API Calls
In recent years, Large Language Models (LLMs) have made significant advancements in various tasks such as mathematical reasoning and program synthesis. However, their ability to effectively use tools via Application Programming Interface (API) calls remains a challenge. Even state-of-the-art LLMs like GPT-4 struggle with generating accurate input arguments and often hallucinate incorrect API call usage. To address this issue, researchers from the University of California Berkeley recently introduced Gorilla, a finetuned LLaMA-based model that outperforms GPT-4 in writing API calls.
Gorilla: A Finetuned LLaMA Model for Writing APIs
Gorilla is a finetuned version of the Latent Language Model Architecture (Llama). It demonstrates strong adaptability to test-time document changes when combined with a document retriever. This enables flexible user updates or version changes and mitigates the problem of hallucination commonly encountered when directly prompting LLMs. To evaluate Gorilla's performance, the researchers introduce APIBench - a comprehensive dataset consisting of HuggingFace, TorchHub, and TensorHub APIs. The successful integration of the retrieval system with Gorilla showcases its potential for accurately using tools while keeping up with frequently updated documentation and improving the reliability and applicability of its outputs. The availability of Gorilla's code, model, data, and demo at https://gorilla.cs.berkeley.edu further facilitates its adoption by developers who wish to utilize it for their projects or research purposes.
The Potential Impact Of Empowering LLMs With External Tools
The paper also highlights the importance of empowering LLMs to use external tools for accessing larger knowledge bases quickly while remaining reliable even when faced with frequent updates or version changes due to user updates or software versions changing over time . Techniques like Gorilla enhance an LLM's ability to identify appropriate APIs for specific tasks; correct usage of APIs improves an LLM's interaction with tools in various domains which can revolutionize various industries by providing them powerful interfaces that enable them access large knowledge bases quickly while remaining reliable even when faced with frequent updates or version changes . The proposed pipeline for finetuning LLMs to call APIs surpasses GPT-4’s performance in massive datasets collected by the researchers from companies like Samsung SDS , Uber ,and VMware . Overall , these advancements contribute towards expanding capabilities of language models as well as their potential applications across different fields .
