arxiv
PublishedJuly 3, 2026 at 4:00 AM
Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging
Publisher summary· verbatim
arXiv:2510.17426v3 Announce Type: replace-cross 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-of
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivThe Steering Budget: Examples beat Knobs9harxivPolestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs9harxivRxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination9harxivValue Leakage: An LLM's Answers Are Silently Shaped by Its Own Values9hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗