Von Zero-Shot-Prompten bis RAG – Teil 3: Chain-of-Thought Prompting
Few-Shot Prompting is an effective and flexible method of preparing language models for new tasks - without any additional training.
Since ChatGPT 2022 was released, a lot has happened in the world of large language models. While older models were still limited to a direct response, it is now almost standard for models to have a reasoning capability. So they think before they answer. The Chain-Of-Thought prompting method, which we will take a closer look at today, attempts to do something similar. Even though models today have reasoning capabilities, this method should not be underestimated. Reasoning and Chain-Of-Thought can complement each other and allow even less expensive models to achieve valuable results
