Generative language models produce highly abstractive outputs by design, in contrast to extractive responses in search engines. Given this characteristic of LLMs and the resulting implications for content Licensing & Attribution, we propose the the so-called Extractive-Abstractive axis for benchmarking generative models and highlight the need for developing corresponding metrics, datasets and annotation guidelines. We limit our discussion to the text modality.

翻译：生成式语言模型天生设计为产生高度抽象的输出，这与搜索引擎中的抽取式响应形成对比。基于LLM的这一特性及其对内容许可与归属的影响，我们提出了所谓的“抽取-抽象轴”，用于对生成式模型进行基准测试，并强调开发相应度量标准、数据集和标注指南的必要性。本文将讨论范围限定在文本模态。