# Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study

arXiv: https://arxiv.org/abs/2605.14845 · HTML: https://mlsanity.com/paper/2605.14845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainability](https://mlsanity.com/paper/2401.13641/) (2024)
- [DeepSign: Deep On-Line Signature Verification](https://mlsanity.com/paper/2002.10119/) (2020)
- [SVC-onGoing: Signature Verification Competition](https://mlsanity.com/paper/2108.06090/) (2021)
- [Exploring Transformers for Behavioural Biometrics: A Case Study in Gait Recognition](https://mlsanity.com/paper/2206.01441/) (2022)
- [Evaluating ChatGPT and GPT-4 for Visual Programming](https://mlsanity.com/paper/2308.02522/) (2023)
- [PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)](https://mlsanity.com/paper/2507.02966/) (2025)
- [Can Vision-Language Models Evaluate Handwritten Math?](https://mlsanity.com/paper/2501.07244/) (2025)
- [Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language](https://mlsanity.com/paper/2207.06897/) (2022)
- [Type2Branch: Keystroke Biometrics based on a Dual-branch Architecture with Attention Mechanisms and Set2set Loss](https://mlsanity.com/paper/2405.01088/) (2024)
- [AirSignatureDB: Exploring In-Air Signature Biometrics in the Wild and its Privacy Concerns](https://mlsanity.com/paper/2508.08502/) (2025)

## Abstract (arXiv)

Recent advancements in Vision-Language Models (VLMs) have demonstrated strong capabilities in general visual reasoning, yet their applicability to rigorous biometric tasks remains unexplored. This work presents an exploratory study evaluating the zero-shot performance of state-of-the-art VLMs (GPT-5.2 and Gemini 2.5 Pro) on the Signature Verification Challenge (SVC) benchmark. To enable visual processing, raw kinematic time-series are converted into static images, encoding pressure information into stroke opacity whenever available in the source data. Furthermore, we introduce a scoring protocol that extracts latent token probabilities to compute robust biometric scores. Experimental results reveal a significant performance dichotomy dependent on signal quality and forgery type. In random forgery scenarios, the zero-shot VLM achieves exceptional discrimination, with GPT-5.2 reaching an Equal Error Rate of 0.32% in mobile tasks, outperforming supervised state-of-the-art systems. Conversely, in skilled forgery scenarios, where the task is more challenging because both signatures are almost identical, the results are significantly worse, and a critical "Rationalization Trap" emerges: chain-of-thought (CoT) reasoning degrades performance as the model produces kinematic hallucinations to justify forgery artifacts as natural variability.