Zero-shot prompting is the default mode for ChatGPT and most chat interfaces: 'Translate this to Spanish,' 'Summarize this article,' 'Write a python function that...' — no examples needed because the model has seen millions of these in training. The opposite of few-shot. For tasks well-represented in training data (common languages, common tasks, common domains), zero-shot works great. For specialized tasks (your brand's voice, your company's domain), few-shot or fine-tuning beat zero-shot. Modern models are dramatically better at zero-shot than 2020-era models, which is why most users never need to bother with few-shot.
СЛОВАРЬ
Что такое Zero-shot?
Asking an LLM to do a task with no examples in the prompt — relying purely on the model's pre-trained knowledge.
СВЯЗАННЫЕ ТЕРМИНЫ
Few-shot Prompting
Showing an LLM 1-5 examples of input-output pairs in the prompt, before asking it to handle a new input — dramatically improves accuracy.
Prompt Engineering
The practice of crafting input text (prompts) to get the best output from an LLM. A vague prompt gives vague answers; a structured prompt gives precise ones.
LLM (Large Language Model)
An AI system trained on massive text datasets to predict and generate human-like text — the technology behind ChatGPT, Claude, Gemini, and most modern AI chatbots.
Назад к Словарь ИИ