Do Language Models Plagiarize?
Do Language Models Plagiarize?
复制标题
DOI：
10.1145/3543507.3583199
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Jooyoung Lee;Thai Le;Jinghui Chen;Dongwon Lee
中科院分区：
文献类型：
--
作者：
Jooyoung Lee;Thai Le;Jinghui Chen;Dongwon Lee
过去的文献表明，语言模型（LM）通常会记住部分训练实例，并在自然语言生成（NLG）过程中重现它们。然而，尚不清楚 LM 在多大程度上“重用”训练语料库。例如，模型可以生成与训练样本上下文相似的释义句子。因此，在这项工作中，我们研究了 GPT-2 生成文本中的三种抄袭（即逐字抄袭、释义抄袭和思想抄袭），并与其训练数据进行比较，并进一步分析了在实践中广泛使用的具有特定领域语料库的微调语言模型的抄袭模式。我们的研究结果表明，（1）三种类型的抄袭行为在语言模型中广泛存在，超出了记忆范围；（2）语言模型的大小和解码方法与它们表现出的抄袭程度密切相关；（3）经过微调的语言模型的抄袭模式根据其语料库的相似性和同质性而变化。鉴于大多数 LM 的训练数据都是在没有通知内容所有者的情况下从网络上抓取的，因此他们将训练集中的单词、短语甚至核心思想重复到生成的文本中具有道德含义。随着 LM 规模和训练数据的增加，它们的模式可能会加剧，引发人们对不加区别地追求更大训练语料库的更大模型的担忧。抄袭内容还可能包含个人的个人信息和敏感信息。这些发现总体上对当前 LM 在关键任务写作任务中的实用性提出了质疑，并敦促围绕观察到的现象进行更多讨论。数据和源代码可在 https://github.com/Brit7777/LM-plagiarism 获取。
Past literature has illustrated that language models (LMs) often memorize parts of training instances and reproduce them in natural language generation (NLG) processes. However, it is unclear to what extent LMs “reuse” a training corpus. For instance, models can generate paraphrased sentences that are contextually similar to training samples. In this work, therefore, we study three types of plagiarism (i.e., verbatim, paraphrase, and idea) among GPT-2 generated texts, in comparison to its training data, and further analyze the plagiarism patterns of fine-tuned LMs with domain-specific corpora which are extensively used in practice. Our results suggest that (1) three types of plagiarism widely exist in LMs beyond memorization, (2) both size and decoding methods of LMs are strongly associated with the degrees of plagiarism they exhibit, and (3) fine-tuned LMs’ plagiarism patterns vary based on their corpus similarity and homogeneity. Given that a majority of LMs’ training data is scraped from the Web without informing content owners, their reiteration of words, phrases, and even core ideas from training sets into generated texts has ethical implications. Their patterns are likely to exacerbate as both the size of LMs and their training data increase, raising concerns about indiscriminately pursuing larger models with larger training corpora. Plagiarized content can also contain individuals’ personal and sensitive information. These findings overall cast doubt on the practicality of current LMs in mission-critical writing tasks and urge more discussions around the observed phenomena. Data and source code are available at https://github.com/Brit7777/LM-plagiarism.