在大语言模型训练中使用唯一标识符保护版权材料
Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
AI总结:
针对LLM训练中版权保护与成员推理难题,提出“插入与检测”方法,通过嵌入“幽灵句子”等唯一标识符并配合最后k个词测试或困惑度测试,实现可靠、易用的独立成员推理。
摘要:
训练大型语言模型(LLMs)的一个主要问题是它们是否会滥用受版权保护的在线文本。随着训练数据规模的扩大和LLMs在日常生活中的普及,出现了两个问题:1)被相似样本误导的假阳性成员推理结果;2)成员推理方法通常过于复杂,终端用户难以理解和使用。为了解决这些问题,我们提出了一种替代的“插入与检测”方法,主张网络用户和内容平台采用唯一标识符进行可靠且独立的成员推理。用户和平台可以创建自己的标识符,将其嵌入受版权保护的文本中,并在未来的LLMs中独立检测它们。作为初步演示,我们引入了“幽灵句子”和一种用户友好的最后k个词测试,允许终端用户通过与LLMs对话进行成员推理。幽灵句子主要由随机自然词的唯一密码短语组成,可以附带自定义元素以绕过可能的过滤规则。最后k个词测试要求幽灵句子有显著的重复次数(≥10)。对于重复次数较少的情况,我们设计了一个额外的困惑度测试,因为LLMs在遇到不自然的密码短语时会表现出高困惑度。我们还对幽灵句子的记忆和成员推理进行了全面研究,考察了训练数据规模、模型大小、重复次数、插入位置、密码短语词表、对齐等因素。我们的研究表明了在真实场景中应用幽灵句子的可能性,并为潜在应用提供了指导。
英文摘要:
A primary concern regarding training large language models (LLMs) is whether they abuse copyrighted online text. With the increasing training data scale and the prevalence of LLMs in daily lives, two problems arise: \textbf{1)} false positive membership inference results misled by similar examples; \textbf{2)} membership inference methods are usually too complex for end users to understand and use. To address these issues, we propose an alternative \textit{insert-and-detect} methodology, advocating that web users and content platforms employ \textbf{\textit{unique identifiers}} for reliable and independent membership inference. Users and platforms can create their identifiers, embed them in copyrighted text, and independently detect them in future LLMs. As an initial demonstration, we introduce \textit{\textbf{ghost sentences}} and a user-friendly last-$k$ words test, allowing end users to chat with LLMs for membership inference. Ghost sentences consist primarily of unique passphrases of random natural words, which can come with customized elements to bypass possible filter rules. The last-$k$ words test requires a significant repetition time of ghost sentences~($\ge10$). For cases with fewer repetitions, we designed an extra perplexity test, as LLMs exhibit high perplexity when encountering unnatural passphrases. We also conduct a comprehensive study on the memorization and membership inference of ghost sentences, examining factors such as training data scales, model sizes, repetition times, insertion positions, wordlist of passphrases, alignment, \textit{etc}. Our study shows the possibility of applying ghost sentences in real scenarios and provides instructions for the potential application.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。