🟢 Introduction

This chapter covers how to make completions more reliable, as well as how to implement checks to ensure that outputs are reliable.

To a certain extent, most of the previous techniques covered have to do with improving completion accuracy, and thus reliability, in particular self-consistency¹. However, there are a number of other techniques that can be used to improve reliability, beyond basic prompting strategies.

LLM have been found to be more reliable than we might expect at interpreting what a prompt is trying to say when responding to misspelled, badly phrased, or even actively misleading prompts². Despite this ability, they still exhibit various problems including hallucinations³, flawed explanations with CoT prompting methods³, and multiple biases including majority label bias, recency bias, and common token bias⁴. Additionally, zero-shot CoT can be particularly biased when dealing with sensitive topics⁵.

Common solutions to some of these problems include calibrators to remove a priori biases, and verifiers to score completions, as well as promoting diversity in completions.