Prompt Engineering Best Practices: LLM Output Validation & Evaluation

Author(s): Youssef Hosni

Originally published on Towards AI.

Validating Output from Instruction-Tuned LLMs

Checking outputs before showing them to users can be important for ensuring the quality, relevance, and safety of the responses provided to them or used in automation flows.

In this article, we will learn how to use the Moderation API by OpenAI to ensure safety and free of harassment output. Also, we will learn how to use additional prompts to the model to evaluate output quality before displaying them to the user to ensure the generated output follows the given instructions and is free of hallucinations.

This article is the eighth part of the ongoing series Prompt Engineering Best Practices:

Prompt Engineering Best Practices for Instruction-Tuned LLM [Part 1]Prompt Engineering Best Practices for Instruction-Tuned LLM [Part 2]Prompt Engineering for Instruction-Tuned LLM: Iterative Prompt DevelopmentPrompt Engineering for Instruction-Tuned LLM: Text SummarizationPrompt Engineering for Instruction-Tuned LLM: Textual Inference & Sentiment AnalysisPrompt Engineering for Instruction-Tuned LLM: Text Transforming & TranslationPrompt Engineering Best Practices: Chain of Thought ReasoningPrompt Engineering Best Practices: LLM Output Validation [You are here!]Setting Up Working Environment & Getting StartedChecking Harmful OutputChecking Instruction Following

Most insights I share in Medium have previously been shared in my weekly newsletter, To Data & Beyond.

If you want to be up-to-date with the frenetic world of AI while also… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI