*Online* Gorilla: Large Language Models Connected with Massive APIs

**Only use this for online attendance. If you attend in person, please register here: https://www.meetup.com/ucl-natural-language-processing-meetup/events/296928015/

We are delighted to have Shishir Patil (UC Berkeley) present "Gorilla: Large Language Models Connected with Massive APIs".

Abstract: LLMs have seen an impressive wave of advances, 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, 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 LLM that surpasses the performance of all close-sourced and open-sourced LLMs on writing API calls. When combined with a document retriever, Gorilla demonstrates a strong capability to adapt to test-time document changes, enabling flexible API updates and version changes. Gorilla also presents a novel PL inspired metric to measure hallucination, commonly encountered in LLMs. Gorilla is an open-source project having served hundreds of thousand user requests, with enterprise adoption, and an energetic community supporting it. Check out the project at https://gorilla.cs.berkeley.edu/

Bio: Shishir G. Patil is a CS PhD student at UC Berkeley, with the Berkeley AI Research (BAIR) and Sky Computing labs. He is interested in designing and building efficient machine-learning systems for the two extremes - edge and multi-cloud. Recently, he is focused on teaching LLMs to use tools through API calls. His works include Gorilla LLM, MemGPT, Skyplane, and POET. He was a Research Fellow at Microsoft Research before starting his PhD, and has interned at Amazon Science, Apple, and Google Brain.