Also known as: Chain of thought Prompting
Chain-of-thought prompting es una técnica de ingeniería de prompts que pide a un modelo de lenguaje resolver un problema paso a paso antes de dar una respuesta. Se utiliza a menudo para tareas que implican razonamiento, cálculo, planificación o toma de decisiones compleja, aunque la explicación visible puede no reflejar plenamente el procesamiento interno del modelo.
A prompt engineering technique that encourages a large language model (LLM) to explain its reasoning, step by step. For example, consider the following prompt, paying particular attention to the second sentence: How many g forces would a driver experience in a car that goes from 0 to 60 miles per hour in 7 seconds? In the answer, show all relevant calculations. The LLM's response would likely: - Show a sequence of physics formulas, plugging in the values 0, 60, and 7 in appropriate places. - Explain why it chose those formulas and what the various variables mean. Chain-of-thought prompting forces the LLM to perform all the calculations, which might lead to a more correct answer. In addition, chain-of-thought prompting enables the user to examine the LLM's steps to determine whether or not the answer makes sense.