paper-with-me

Papers

Natural Fingerprints of Large Language Models

2025-04-21 · Teppei Suzuki, Ryokan Ri, Sho Takase

Large language models (LLMs) often exhibit biases -- systematic deviations from expected norms -- in their outputs. These range from overt issues, such as unfair responses, to subtler patterns that can reveal which model produced them. We investigate the factors that give rise to identifiable characteristics in LLMs. Since LLMs model training data distribution, it is reasonable that differences in training data naturally lead to the characteristics. However, our findings reveal that even when LLMs are trained on the exact same data, it is still possible to distinguish the source model based on its generated text. We refer to these unintended, distinctive characteristics as natural fingerprints. By systematically controlling training conditions, we show that the natural fingerprints can emerge from subtle differences in the training process, such as parameter sizes, optimization settings, and even random seeds. We believe that understanding natural fingerprints offers new insights into the origins of unintended bias and ways for improving control over LLM behavior.

📄 PDF Abstract BibTeX arXiv:2504.14871

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From Construction to Injection: Edit-Based Fingerprints for Large Language Models

2025-09-03 · Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui 외 arxiv

Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misuse. In black-box deployment, verification is hindered by defensive filtering of…

ImF: Implicit Fingerprint for Large Language Models

2025-03-25 · Wu jiaxuan, Peng Wanli, Fu hang, Xue Yiming 외

Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for e…

Adversarial AttackQuestion Answering

Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models

2026-07-28 · Yongyi Cui, Yue Li, Tianbao Jiang, Xin Yi arxiv

Large language models (LLMs) are costly intellectual assets that remain exposed to unauthorized redistribution and commercial misuse. Injected fingerprints, i.e., trigger--target pairs embedded in model behavior, offer a…

Visual Fingerprints for LLM Generation Comparison

2026-05-07 · Amal Alnouri, Andreas Hinterreiter, Christina Humer, Furui Cheng 외 arxiv

Large language model (LLM) outputs arise from complex interactions among prompts, system instructions, model parameters, and architecture. We refer to specific configurations of these factors as generation conditions, ea…

Text Generation

SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery

2019-11-12 · Shion Honda, Shoi Shi, Hiroki R. Ueda

In drug-discovery-related tasks such as virtual screening, machine learning is emerging as a promising way to predict molecular properties. Conventionally, molecular fingerprints (numerical representations of molecules) …

Drug DiscoveryLanguage ModelingLanguage ModellingSmall Data Image Classification+1