通过局部信息探测，评估大模型生成侵权内容的风险。
Measuring Copyright Risks of Large Language Model via Partial Information Probing
- 用部分原文提示模型续写，测试其生成侵权内容的能力。
- 模型在仅获部分文本时仍能生成与原文高度重合的内容。
- 适合关注AI版权风险与内容安全的研究者和开发者。
探索大语言模型（LLMs）训练数据来源是检测其潜在版权侵权的重要方向。尽管该方法可识别训练数据中可能包含的受版权保护内容，但无法直接衡量侵权风险。近期研究转向测试模型是否能直接输出受版权保护的内容。本文通过向模型提供受版权保护材料的部分信息，探究并评估其生成侵权内容的能力，并尝试使用迭代提示促使模型生成更多侵权内容。具体而言，将受版权保护文本的一部分输入模型，提示其完成续写，并分析生成内容与原始文本之间的重叠程度。研究结果表明，即使仅提供部分输入，模型也能生成与受版权保护材料高度重合的内容。
原文摘要 · Abstract (English)
Exploring the data sources used to train Large Language Models (LLMs) is a crucial direction in investigating potential copyright infringement by these models. While this approach can identify the possible use of copyrighted materials in training data, it does not directly measure infringing risks. Recent research has shifted towards testing whether LLMs can directly output copyrighted content. Addressing this direction, we investigate and assess LLMs' capacity to generate infringing content by providing them with partial information from copyrighted materials, and try to use iterative prompting to get LLMs to generate more infringing content. Specifically, we input a portion of a copyrighted text into LLMs, prompt them to complete it, and then analyze the overlap between the generated content and the original copyrighted material. Our findings demonstrate that LLMs can indeed generate content highly overlapping with copyrighted materials based on these partial inputs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。