Saved in:
Bibliographic Details
Main Authors: Casey, Emma, Roberts, David, Sim, David, Beaver, Ian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.27082
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910177873100800
author Casey, Emma
Roberts, David
Sim, David
Beaver, Ian
author_facet Casey, Emma
Roberts, David
Sim, David
Beaver, Ian
contents We present a framework for migrating production Large Language Model (LLM) based systems when the underlying model reaches end-of-life or requires replacement. The key contribution is a Bayesian statistical approach that calibrates automated evaluation metrics against human judgments, enabling confident model comparison even with limited manual evaluation data. We demonstrate this framework on a commercial question-answering system serving 5.3M monthly interactions across six global regions; evaluating correctness, refusal behavior, and stylistic adherence to successfully identify suitable replacement models. The framework is broadly applicable to any enterprise deploying LLM-based products, providing a principled, reproducible methodology for model migration that balances quality assurance with evaluation efficiency. This is a capability increasingly essential as the LLM ecosystem continues to evolve rapidly and organizations manage portfolios of AI-powered services across multiple models, regions, and use cases.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27082
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems
Casey, Emma
Roberts, David
Sim, David
Beaver, Ian
Artificial Intelligence
Machine Learning
Software Engineering
We present a framework for migrating production Large Language Model (LLM) based systems when the underlying model reaches end-of-life or requires replacement. The key contribution is a Bayesian statistical approach that calibrates automated evaluation metrics against human judgments, enabling confident model comparison even with limited manual evaluation data. We demonstrate this framework on a commercial question-answering system serving 5.3M monthly interactions across six global regions; evaluating correctness, refusal behavior, and stylistic adherence to successfully identify suitable replacement models. The framework is broadly applicable to any enterprise deploying LLM-based products, providing a principled, reproducible methodology for model migration that balances quality assurance with evaluation efficiency. This is a capability increasingly essential as the LLM ecosystem continues to evolve rapidly and organizations manage portfolios of AI-powered services across multiple models, regions, and use cases.
title When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems
topic Artificial Intelligence
Machine Learning
Software Engineering
url https://arxiv.org/abs/2604.27082