Prompt engineering
Below is an excerpt from the official OpenAI prompt engineering recommendations page.
Strategy: Give models time to "think"
Tactic: Instruct the model to work out its own solution before rushing to a conclusion
Sometimes we get better results when we explicitly instruct the model to reason from first principles before coming to a conclusion. Suppose for example we want a model to evaluate a student’s solution to a math problem. The most obvious way to approach this is to simply ask the model if the student's solution is correct or not.
SYSTEMDetermine if the student's solution is correct or not.
USERProblem Statement: I'm building a solar power installation and I need help working out the financials.- Land costs $100 / square foot- I can buy solar panels for $250 / square foot- I negotiated a contract for maintenance that will cost me a flat $100k per year, and an additional $10 / square footWhat is the total cost for the first year of operations as a function of the number of square feet.
Student's Solution: Let x be the size of the installation in square feet.1. Land cost: 100x2. Solar panel cost: 250x3. Maintenance cost: 100,000 + 100xTotal cost: 100x + 250x + 100,000 + 100x = 450x + 100,000
ASSISTANTThe student's solution is correct.
But the student's solution is actually not correct! We can get the model to successfully notice this by prompting the model to generate its own solution first.
SYSTEMFirst work out your own solution to the problem. Then compare your solution to the student's solution and evaluate if the student's solution is correct or not. Don't decide if the student's solution is correct until you have done the problem yourself.
USERProblem Statement: I'm building a solar power installation and I need help working out the financials.- Land costs $100 / square foot- I can buy solar panels for $250 / square foot- I negotiated a contract for maintenance that will cost me a flat $100k per year, and an additional $10 / square footWhat is the total cost for the first year of operations as a function of the number of square feet.
Student's Solution: Let x be the size of the installation in square feet.1. Land cost: 100x2. Solar panel cost: 250x3. Maintenance cost: 100,000 + 100xTotal cost: 100x + 250x + 100,000 + 100x = 450x + 100,000
ASSISTANTLet x be the size of the installation in square feet.1. Land cost: 100x2. Solar panel cost: 250x3. Maintenance cost: 100,000 + 10xTotal cost: 100x + 250x + 100,000 + 10x = 360x + 100,000
The student's solution is incorrect. They made an error in the maintenance cost calculation, using 100x instead of 10x. The correct total cost for the first year of operations is 360x + 100,000.
Tactic: Use inner monologue or a sequence of queries to hide the model's reasoning process
The previous tactic demonstrates that it is sometimes important for the model to reason in detail about a problem before answering a specific question. For some applications, the reasoning process that a model uses to arrive at a final answer would be inappropriate to share with the user. For example, in tutoring applications we may want to encourage students to work out their own answers, but a model’s reasoning process about the student’s solution could reveal the answer to the student.
Inner monologue is a tactic that can be used to mitigate this. The idea of inner monologue is to instruct the model to put parts of the output that are meant to be hidden from the user into a structured format that makes parsing them easy. Then before presenting the output to the user, the output is parsed and only part of the output is made visible.
SYSTEMFollow these steps to answer the user queries.
Step 1 - First work out your own solution to the problem. Don't rely on the student's solution since it may be incorrect. Enclose all your work for this step within triple quotes (""").
Step 2 - Compare your solution to the student's solution and evaluate if the student's solution is correct or not. Enclose all your work for this step within triple quotes (""").
Step 3 - If the student made a mistake, determine what hint you could give the student without giving away the answer. Enclose all your work for this step within triple quotes (""").
Step 4 - If the student made a mistake, provide the hint from the previous step to the student (outside of triple quotes). Instead of writing "Step 4 - ..." write "Hint:".
USERProblem Statement: <insert problem statement>
Student Solution: <insert student solution>
Alternatively, this can be achieved with a sequence of queries in which all except the last have their output hidden from the end user.
First, we can ask the model to solve the problem on its own. Since this initial query doesn't require the student’s solution, it can be omitted. This provides the additional advantage that there is no chance that the model’s solution will be biased by the student’s attempted solution.
USER<insert problem statement>
Next, we can have the model use all available information to assess the correctness of the student’s solution.
SYSTEMCompare your solution to the student's solution and evaluate if the student's solution is correct or not.USERProblem statement: """<insert problem statement>"""
Your solution: """<insert model generated solution>"""
Student’s solution: """<insert student's solution>"""
Finally, we can let the model use its own analysis to construct a reply in the persona of a helpful tutor.
SYSTEMYou are a math tutor. If the student made an error, offer a hint to the student in a way that does not reveal the answer. If the student did not make an error, simply offer them an encouraging comment.USERProblem statement: """<insert problem statement>"""
Your solution: """<insert model generated solution>"""
Student’s solution: """<insert student's solution>"""
Analysis: """<insert model generated analysis from previous step>"""