Large language models (LLMs) often struggle with processing extensive input contexts, which can lead to redundant, inaccurate, or incoherent summaries. Recent methods have used unstructured memory to incrementally process these contexts, but they still suffer from information overload due to the volume of unstructured data handled. In our study, we introduce structured knowledge representations ($GU_{json}$), which significantly improve summarization performance by 40% and 14% across two public datasets. Most notably, we propose the Chain-of-Key strategy ($CoK_{json}$) that dynamically updates or augments these representations with new information, rather than recreating the structured memory for each new source. This method further enhances performance by 7% and 4% on the datasets.

本研究解决了大语言模型在处理大量输入上下文时面临的信息冗余和不一致性问题。我们引入结构化知识表示（$GU_{json}$），并提出动态更新的Chain-of-Key策略（$CoK_{json}$），显著提高了摘要性能，分别在两个公共数据集上提高了40%和14%。该方法通过更有效的信息整合，进一步提升了7%和4%的性能，具有重要的实际应用价值。

通过结构化表示增强增量摘要