Zero-shot VLMs like GPT-5.2 achieve very low error rates on random forgeries in signature verification but perform poorly on skilled forgeries and are harmed by chain-of-thought reasoning.
Beware the Rationalization Trap! When Lan- guage Model Explainability Diverges From Our Mental Models of Language,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study
Zero-shot VLMs like GPT-5.2 achieve very low error rates on random forgeries in signature verification but perform poorly on skilled forgeries and are harmed by chain-of-thought reasoning.