Gorilla: Large Language Model Connected with Massive APIs

Our summary

Connects an LLM to large API collections and documents the tendency to hallucinate API calls and arguments when prompted directly; retrieval-aware training reduces but does not eliminate the fabrication.

Why it matters

Direct evidence that tool and function calls can be confidently fabricated — the core risk for agents that act on generated calls.

Related findings (1)

• Hallucinated tool/function argumentsHigh

  When calling tools, models invent argument values or call functions that weren't provided.

Cite this