GPT-4: Researchers from Berkeley and Microsoft have developed Gorilla, a finetuned LLaMA-based model that outperforms GPT-4 in generating precise API calls. The team created the APIBench dataset to finetune Gorilla, which demonstrates improved API call-generating capabilities and the ability to adapt to updated documentation. This breakthrough addresses issues of hallucination and reliability in large language models, enhancing their performance and task comprehension.
Read more at MarkTechPost…