Large Language Models (LLMs) are increasingly using external web content. However, much of this content is not easily digestible by LLMs due to LLM-unfriendly formats and limitations of context length. To address this issue, we propose a method for generating general-purpose, information-dense summaries that act as plain-text repositories of web content. Inspired by Hegel's dialectical method, our approach, denoted as Chain of Summaries (CoS), iteratively refines an initial summary (thesis) by identifying its limitations through questioning (antithesis), leading to a general-purpose summary (synthesis) that can satisfy current and anticipate future information needs. Experiments on the TriviaQA, TruthfulQA, and SQUAD datasets demonstrate that CoS outperforms zero-shot LLM baselines by up to 66\% and specialized summarization methods such as Chain of Density, BRIO and PEGASUS by up to 27\%. CoS-generated summaries yield higher Q\&A performance compared to the source content, while requiring substantially fewer tokens and being agnostic to the specific downstream LLM. CoS thus resembles an appealing option for website maintainers to make their content more accessible for LLMs, while retaining possibilities for human oversight.

翻译：大型语言模型（LLM）日益依赖外部网络内容，但由于LLM不友好的格式和上下文长度限制，这些内容往往难以被有效消化。为解决这一问题，我们提出一种生成通用信息密集型摘要的方法，使其作为网络内容的纯文本存储库。受黑格尔辩证法启发，本方法称为摘要链（CoS），通过提问识别初始摘要（正题）的局限性（反题），迭代优化得到通用摘要（合题），从而满足当前及预期的未来信息需求。在TriviaQA、TruthfulQA和SQUAD数据集上的实验表明，CoS在零样本LLM基线上的性能提升最高达66%，在Chain of Density、BRIO和PEGASUS等专用摘要方法上的提升最高达27%。与原始内容相比，CoS生成的摘要能以显著更少的词元实现更高的问答性能，且不依赖特定下游LLM。因此，CoS为网站维护者提供了一种有吸引力的选择，既能使其内容更易于被LLM获取，同时保留人工监督的可能性。