Natural Fingerprints of Large Language Models
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
From Construction to Injection: Edit-Based Fingerprints for Large Language Models
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
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 AnsweringConstruction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models
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
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 GenerationSMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery
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