中文
相关论文

相关论文: Natural Fingerprints of Large Language Models

200 篇论文

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, each of which can bias…

人工智能 · 计算机科学 2026-05-08 Amal Alnouri , Andreas Hinterreiter , Christina Humer , Furui Cheng , Marc Streit

It has been shown that finetuned transformers and other supervised detectors effectively distinguish between human and machine-generated text in some situations arXiv:2305.13242, but we find that even simple classifiers on top of n-gram and…

计算与语言 · 计算机科学 2024-05-24 Hope McGovern , Rickard Stureborg , Yoshi Suhara , Dimitris Alikaniotis

Fingerprinting Large Language Models (LLMs)is essential for provenance verification and model attribution. Existing fingerprinting methods are primarily evaluated after fine-tuning, where models have already acquired stable signatures from…

密码学与安全 · 计算机科学 2026-04-15 Yao Tong , Haonan Wang , Siquan Li , Kenji Kawaguchi , Tianyang Hu

We investigate fingerprints in pretraining datasets for large language models (LLMs) through dataset classification experiments. Building on prior work demonstrating the existence of fingerprints or biases in popular computer vision…

机器学习 · 计算机科学 2025-12-02 Youssef Mansour , Reinhard Heckel

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

机器学习 · 计算机科学 2026-03-03 Yiwei Chen , Soumyadeep Pal , Yimeng Zhang , Qing Qu , Sijia Liu

Large language models (LLMs) have distinct and consistent stylistic fingerprints, even when prompted to write in different writing styles. Detecting these fingerprints is important for many reasons, among them protecting intellectual…

计算与语言 · 计算机科学 2025-03-04 Yehonatan Bitton , Elad Bitton , Shai Nisan

Current benchmarks for Large Language Models (LLMs) primarily focus on performance metrics, often failing to capture the nuanced behavioral characteristics that differentiate them. This paper introduces a novel ``Behavioral Fingerprinting''…

计算与语言 · 计算机科学 2025-09-08 Zehua Pei , Hui-Ling Zhen , Ying Zhang , Zhiyuan Yang , Xing Li , Xianzhi Yu , Mingxuan Yuan , Bei Yu

Large Language Models (LLMs) have been observed to process non-human-readable text sequences, such as jailbreak prompts, often viewed as a bug for aligned LLMs. In this work, we present a systematic investigation challenging this…

The exorbitant cost of training Large language models (LLMs) from scratch makes it essential to fingerprint the models to protect intellectual property via ownership authentication and to ensure downstream users and developers comply with…

密码学与安全 · 计算机科学 2024-04-04 Jiashu Xu , Fei Wang , Mingyu Derek Ma , Pang Wei Koh , Chaowei Xiao , Muhao Chen

Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel fingerprinting framework that leverages the behavioral patterns…

密码学与安全 · 计算机科学 2026-02-11 Zhenyu Xu , Victor S. Sheng

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…

计算与语言 · 计算机科学 2025-02-18 Shu Yang , Shenzhe Zhu , Liang Liu , Lijie Hu , Mengdi Li , Di Wang

Fingerprinting refers to the process of identifying underlying Machine Learning (ML) models of AI Systemts, such as Large Language Models (LLMs), by analyzing their unique characteristics or patterns, much like a human fingerprint. The…

机器学习 · 计算机科学 2025-02-10 Devansh Bhardwaj , Naman Mishra

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

机器学习 · 计算机科学 2024-04-22 Diego Calanzone , Stefano Teso , Antonio Vergari

Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text, but also provide a very sophisticated probabilistic model of language use. Since generating a semantically consistent text requires a…

计算与语言 · 计算机科学 2024-04-09 Romuald A. Janik

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

计算与语言 · 计算机科学 2025-07-15 Itay Itzhak , Yonatan Belinkov , Gabriel Stanovsky

As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and…

密码学与安全 · 计算机科学 2025-07-09 Saeif Alhazbi , Ahmed Mohamed Hussain , Gabriele Oligeri , Panos Papadimitratos

The development of large language models (LLMs) is costly and has significant commercial value. Consequently, preventing unauthorized appropriation of open-source LLMs and protecting developers' intellectual property rights have become…

计算与语言 · 计算机科学 2026-02-02 Yiheng Liu , Junhao Ning , Sichen Xia , Haiyang Sun , Yang Yang , Hanyang Chi , Xiaohui Gao , Ning Qiang , Bao Ge , Junwei Han , Xintao Hu

Reliable evaluation is essential in machine learning research, yet methodological flaws-particularly data leakage-continue to undermine the validity of reported results. In this work, we investigate whether large language models (LLMs) can…

计算与语言 · 计算机科学 2026-04-17 Domonkos Varga

Citation practices are crucial in shaping the structure of scientific knowledge, yet they are often influenced by contemporary norms and biases. The emergence of Large Language Models (LLMs) introduces a new dynamic to these practices.…

数字图书馆 · 计算机科学 2024-08-27 Andres Algaba , Carmen Mazijn , Vincent Holst , Floriano Tori , Sylvia Wenmackers , Vincent Ginis

Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…

计算与语言 · 计算机科学 2024-09-24 Diego Calanzone , Stefano Teso , Antonio Vergari
‹ 上一页 1 2 3 10 下一页 ›