arXiv cs.CL· Fantong Meng, Chengjie Sun, Shuangjia Yang, Zhiyuan Zhao, Yansheng Pei, Xinyang Li·· 10 小时前AI 评分38
NumPrint：用单条定长整数序列为语言模型做指纹识别
One Sequence Is Enough: Fingerprinting Language Models from Fixed-Length Integer Sequences
AI 导读
研究者提出 NumPrint 基准，用中、日、英三种提示让模型在单次回答中输出 1 到 355 之间的 294 个整数，共收集 51 个模型的 5,036 条答案。
正文 · 原文
Abstract:Users of model APIs and third-party platforms often rely on the declared model name to identify the model responding to their requests. However, the actual model may differ from the declared one, motivating identity verification based on observable outputs. Previous studies have shown that preferences in simple numerical-choice tasks can serve as model fingerprints. We investigate whether a single fixed-length integer sequence can combine multiple numerical observations to identify its source model. For this task, we introduce NumPrint, a benchmark of 5,036 answers from 51 models, collected using Chinese, Japanese, and English prompts that request 294 integers between 1 and 355 in one response. We propose the Shallow MLP and Causal Transformer (SMCT) to capture aggregate numerical preferences and behavioral patterns in generated sequences. In 51-class closed-set evaluation, SMCT achieves 92.72% accuracy from a single sequence, outperforming all methods compared in this study. Using two and four answers increases accuracy to 96.06% and 97.12%, respectively. These results show that a single integer sequence contains useful model fingerprints and that additional answers further improve identification.
| Comments: | 17 pages including appendices, 6 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.14010 [cs.CL] |
| (or arXiv:2611.14010v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14010 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fantong Meng [view email]
[v1]
Tue, 10 Nov 2026 12:50:33 UTC (744 KB)
来源：arXiv cs.CL · arxiv.org