Skip to content
AImpact
IT EN
Medium Agents · 1 min read

Gorilla: fine-tuned LLaMA that calls APIs without errors

In one sentence UC Berkeley presents Gorilla, a retrieval-augmented fine-tuned LLaMA for accurate API calls: reduces API hallucination from 83% to 3%, outperforming GPT-4 on this task.

Verified Official source
ShareLinkedInX
Reading level

One of the most frustrating problems with language models is their tendency to invent nonexistent APIs or call them with wrong parameters. If you're building an agent that needs to interact with real services, this error stops everything.

Gorilla is a fine-tuned LLaMA specifically trained to call APIs accurately. Instead of relying solely on training memory, it uses a retrieval mechanism: it searches for up-to-date API documentation and uses it as context before generating the call.

The result is striking: on a benchmark of over 1600 APIs (HuggingFace, TorchHub, TensorHub), Gorilla reduces errors from 83% to 3%, even outperforming GPT-4 on this specific task despite being much smaller.

Companies

UC Berkeley, Microsoft Research

Tools

Gorilla, LLaMA, APIBench

Tags

UC BerkeleyGorillaLLaMAAPI CallingFine-TuningHallucination

Sources