arxiv
PublishedSeptember 16, 2026 at 4:00 AM
—neutral
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
Publisher summary· verbatim
arXiv:2609.17386v1 Announce Type: new Abstract: Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance. Most existing calibration methods introduce additional regularization terms to promote dispersion acr
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
arxivGeospatial Metadata Improves Discoverability by Connecting Datasets Across Scientific Disciplines11marxivVisual Cue Guided Video Planning for Generalizable Robot Navigation11marxivA unified framework for global and local interpretability using adaptive derivative-ordered random explanation11marxivAfter the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem11mThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗