With generative AI, the devil is in the details, as this post from Hanzo notes, discussing the art and science of prompt engineering.
The post (Leveraging Generative AI in eDiscovery: The Art and Science of Prompt Engineering, written by Aidan Randle-Conde and available here) discusses how, in AI lingo, a ‘prompt’ is a query or instruction that tells the Large Language Model (LLM) what to generate or how to respond. Think of it as a refined search query written in plain language that the average person can understand. Generally, the more precise and relevant your prompt is, the more accurate and useful the AI-generated results will be.
Aidan’s post also provides ten tips for crafting effective prompts to the LLM for eDiscovery. Here’s one of them:
Avoid Hallucinations: A “hallucination” is when an LLM generates a response that contains incorrect information. It can be hard to tell when an LLM generates a hallucination; therefore, it is highly recommended that the factual accuracy of the response be verified. Asking the same question in multiple ways can help to identify and avoid hallucinations.
Avoiding hallucinations is key for the legal industry, which is why Hanzo has adopted a complex strategy of multi-step and multi-faceted prompting for a case. With Spotlight AI, each step and facet addresses a different aspect of the case at hand and can be related back to the description of the case. This strategy gives us much greater confidence that the LLM is behaving correctly.
So, what are the other nine tips for crafting effective prompts to the LLM for eDiscovery? And how can you identify ineffective prompts? Find out here! It’s just one more click! The art and science of prompt engineering is both! 🙂
So, what do you think? Do you feel like you understand the best practices for querying an LLM? Please share any comments you might have or if you’d like to know more about a particular topic.
Image created using Microsoft Bing’s Image Creator Powered by DALL-E, using the term “art and science mixed with technology”.
Disclosure: Hanzo is an Educational Partner and sponsor of eDiscovery Today
Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by my employer, my partners or my clients. eDiscovery Today is made available solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Today should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.