arXiv cs.LG
· Papers
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
arXiv:2607.07395v1 Announce Type: cross Abstract: Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-shot accuracy but often degrades calibration due to entropy-driven overconfidence. Prior approaches mitigate this using LL