English

Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging

Computation and Language 2025-11-03 v2 Artificial Intelligence Machine Learning

Abstract

The "alignment tax" of post-training is typically framed as a drop in task accuracy. We show it also involves a severe loss of calibration, making models overconfident, less reliable, and model outputs less diverse. We show that this trade-off can be navigated effectively via a simple post-hoc intervention: interpolating between a model's weights before and after alignment. Crucially, this is not a strict trade-off. We find that the process consistently reveals Pareto-optimal interpolations - models that improve accuracy beyond both parents while substantially recovering the calibration lost during alignment. Our work demonstrates that simple model merging provides a computationally efficient method for mitigating the full scope of the alignment tax, yielding models that are more capable and more reliable.

Keywords

Cite

@article{arxiv.2510.17426,
  title  = {Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging},
  author = {Tiancheng Hu and Benjamin Minixhofer and Nigel Collier},
  journal= {arXiv preprint arXiv:2510.17426},
  year   = {2025}
}