Beyond the Buzz: Uncovering the Hidden Impact of LLMs on Our Future
GPT-3 was the first model to achieve, purely via text interaction with the model, “strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.”
Today’s LLMs accurately respond to task queries when prompted with task descriptions and examples. However, pre-trained LLMs fail to follow user intent and perform worse in zero-shot settings than in few-shot. Fine-tuning is known to enhance generalization to unseen tasks, improving zero-shot performance significantly. Other improvements relate to either task-specific training or better prompting.
