LSEG Insights

Judging AI with AI: LLM-as-a-Judge: Using AI to Evaluate GenAI Output

Dinesh Kalamegam

AI Engineer, LSEG Analytics

Stanislav Chistyakov 

Data Scientist

David Oliver 

Data Science

As generative AI scales, evaluating the quality of its output becomes increasingly complex. This white paper explores LLM-as-a-Judge - using AI to evaluate AI - highlighting methods like pairwise comparison and direct scoring, while discussing benefits, limitations, and why this approach could be key to building trust in AI systems.

The key points: 

  • Gen AI allows systems to return larger volumes of output to the users. However, traditional ML metrics are harder to apply and Subject Matter Experts (SMEs) won't have time to check the entire output. Therefore we need new means of evaluation that can scale.
  • LLM-as-a-Judge is the notion of using LLMs to evaluate LLM generated outputs. The paper goes through two types of LLM-as-a-Judge implementations that can mimic how an SME would do an evaluation: picking the better between two responses, and scoring a single response based on prompts that can be built with own domain knowledge. 
  • There are some caveats to the method (such as LLM bias and data limitations), which is why it cannot replace SMEs completely. However, the technique can reduce burden on them by being able to leverage the LLM's ability to capture semantic meaning at scale.

Legal Disclaimer

Republication or redistribution of LSE Group content is prohibited without our prior written consent. 

The content of this publication is for informational purposes only and has no legal effect, does not form part of any contract, does not, and does not seek to constitute advice of any nature and no reliance should be placed upon statements contained herein. Whilst reasonable efforts have been taken to ensure that the contents of this publication are accurate and reliable, LSE Group does not guarantee that this document is free from errors or omissions; therefore, you may not rely upon the content of this document under any circumstances and you should seek your own independent legal, investment, tax and other advice. Neither We nor our affiliates shall be liable for any errors, inaccuracies or delays in the publication or any other content, or for any actions taken by you in reliance thereon.

Copyright © 2025 London Stock Exchange Group. All rights reserved.