I need to summarize and answer some questions about articles. For this, I will use language models. I see that GPT-3 works amazingly good for my use case. But, there's also Alpaca.
They both look fine but I wonder how do you specialists know how successful a model is. Where should I look to know this? In software development, you write tests to see if the code works fine for your use-case. How do you do the same for a language processing model? Or, am I looking at something wrong? For example, should I focus on the training data instead?