Framework guides safe and tracked use of AI in critical workflows
MERCI Cards: An LLM Evaluation and Deployment Framework for High-Stakes Domains
Artificial IntelligenceHuman-Computer Interaction
Summary
Using large language models (LLMs) in important areas like criminal justice is risky and complicated. The paper presents a framework that helps people evaluate, monitor, and improve these AI systems carefully over time. This method uses math to balance different goals like accuracy and resource limits, so developers know where to fix problems and users know when to check results. The framework is designed to keep AI use safer and more reliable in sensitive areas.
What this means in practice
- •For criminal justice technology teams: Track and improve performance of AI tools used in legal decision support with weighted evaluations across deployment cycles.
- •For financial risk management teams: Manage AI system monitoring and error checking for resource-constrained, high-risk financial decision workflows.
Authors
Aparna Komarla, Annalisa Szymanski
Abstract
As LLMs are increasingly deployed in high-stakes professional workflows, engineers and researchers require principled protocols to systematically track, monitor, and improve model performance across deployment cycles. We present a mathematical framework for iterative LLM evaluation and deployment, and demonstrate its application to AI systems used in criminal justice. Our framework formalizes LLM integration in high-stakes, high-risk, and resource-constrained domains across model selection, rubric design, evaluations and deployment via a weighted multi-objective optimization. We demonstrate that MERCI Cards can guide improvements of the system across deployment iterations, direct developer attention toward under-performing areas, and focus user attention on validation and error-correction in the LLM's outputs.