Newest papers

Model-intrinsic, Weight-level, and Training-free Spectral Fingerprinting for Large Language Models

Yanan He, Yanli Chen, Ling Xiong, Gejian Zhao, Hanzhou Wu · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30626 · open-access PDF

Chinese

大型语言模型(LLMs)作为开放体重检查点的越来越多的发布和重复使用使得模型指纹对所有权保护和离线审计至关重要。现有的指纹识别方法通常从查询响应、生成输出或输入诱导激活中构建证据。虽然在基于代表性的设置中有效,但它们可以受到即时选择、解码配置、推断环境和前进实施的影响,这可能会限制其适用性。

Machine translation (Meta M2M100); the English original follows.

Abstract

The increasing release and reuse of Large Language Models (LLMs) as open-weight checkpoints make model fingerprinting important for ownership protection and offline auditing. Existing fingerprinting methods typically construct evidence from query responses, generated outputs, or input-induced activations. Although effective in representation-based settings, they can be affected by prompt selection, decoding configuration, inference environment, and forward-pass implementation, which may limit their applicability. Here we introduce a model-intrinsic weight-level framework that derives compact f

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange