LLM Evaluation is a Forecasting Problem

Abstract:Standard procedure in machine learning is to randomly split train and test data, emulating IID draws from one underlying data distribution. In practice, models are trained on past data and deployed in the future, which may come from distinct distributions. In this paper, we find that web text is indeed highly non-stationary, as text distributions shift over time. We further observe that model performance changes continuously over time across diverse benchmarks. Consequently, future model performance is better predicted by measurements made on recent evaluation data, and is best predicted by time series forecasters applied to historic performance rather than by historic performance itself. Choosing which model to deploy based on forecasted accuracy enables more reliable selection of performant models, thus improving downstream accuracy in the regime practitioners care about: deployment. Taken together, our experiments suggest that time should be treated as a fundamental variable in LLM evaluation. We release our code and data.

Machine Learning (cs.LG)

arXiv:2610.17018 [cs.LG]

(or arXiv:2610.17018v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.17018 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.