Training ML Models with Predictable Failures

Will Schwarzer, Scott Niekum

Abstract

Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely large enough to observe the failures that matter. Jones et al. (2025) address this by extrapolating from the largest k failure scores in an evaluation set to predict deployment-scale failure rates. We give a finite-k decomposition of this estimator's forecast error and show that it has a built-in bias toward over-prediction in the typical case, which is the safety-favorable direction. This bias is offset when the evaluation set misses a rare high-failure mode that the deployment set contains, leaving the forecast to under-predict at deployment scale. We propose a fine-tuning objective, the forecastability loss, that addresses this failure mode. In two proof-of-concept experiments, a language-model password game and an RL gridworld, fine-tuning substantially reduces held-out forecast error while preserving primary-task capability and achieving safety similar to that of supervised baselines.
BibTeX
@inproceedings{schwarzer2026training,
  author = {Will Schwarzer and Scott Niekum},
  title = {{Training ML Models with Predictable Failures}},
  booktitle = {AIWILD @ ICML},
  year = {2026},
  url = {https://openreview.net/forum?id=eAFDbSFdlp},
}

Loading related content...

Figure