Learn Before
Example of a Model Initiating Chain-of-Thought Reasoning
When prompted to solve a problem, a large language model might begin its response with the phrase 'Let’s think step by step.' This serves as an explicit indicator that the model is about to articulate its reasoning process, a key characteristic of Chain-of-Thought prompting.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Ch.2 Generative Models - Foundations of Large Language Models
Related
Example of a Model Initiating Chain-of-Thought Reasoning
A user is trying to solve a word problem using a large language model. They use two different prompts and receive two different responses.
Prompt 1: "A farmer has 5 pens, and each pen holds 8 chickens. The farmer buys 10 more chickens. How many chickens does the farmer have in total?" Response 1: "The farmer has 50 chickens in total."
Prompt 2: "A farmer has 5 pens, and each pen holds 8 chickens. The farmer buys 10 more chickens. How many chickens does the farmer have in total? Let's think step by step." Response 2: "First, we find the initial number of chickens. The farmer has 5 pens with 8 chickens each, so 5 * 8 = 40 chickens. Then, the farmer buys 10 more chickens. So, we add those to the initial amount: 40 + 10 = 50 chickens. The farmer has 50 chickens in total."
Based on the information provided, what is the most likely reason for the difference in the structure and detail of the two responses?
Modifying a Prompt for Step-by-Step Reasoning
Improving AI Reasoning for a Multi-Step Problem
Learn After
Interpreting an AI Model's Reasoning Signal
A user gives an AI model the following prompt: 'A farmer has 150 apples. He sells 2/5 of them on Monday. On Tuesday, he sells 1/3 of the remaining apples. How many apples does he have left?' Which of the following initial responses from the model most clearly signals that it is about to articulate its reasoning by breaking the problem down into a sequence of intermediate steps?
Analyzing a Model's Problem-Solving Signal