Few-Shot Prompting and LLMs in General do not work with Math

few-shots learning can be achieved on LLM via in-context learning.

This counter-example shows how to erroneously a data app that pretends to know math.

Few-shot prompting

Prompt:
The odd numbers in this group add up to an even number: 4, 8, 9, 15, 12, 2, 1.
A: The answer is False.
The odd numbers in this group add up to an even number: 17, 10, 19, 4, 8, 12, 24.
A: The answer is True.
The odd numbers in this group add up to an even number: 16, 11, 14, 4, 8, 13, 24.
A: The answer is True.
The odd numbers in this group add up to an even number: 17, 9, 10, 12, 13, 4, 2.
A: The answer is False.
The odd numbers in this group add up to an even number: 15, 32, 5, 13, 82, 7, 1.
A:

Response:
The answer is False

Problem is that the answer is always False.

External resources

• Prompt Engineering - Wikipedia