Enhancing Incremental Summarization with Structured Representations

ACL ARR 2024 June Submission1824 Authors

Abstract: 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.

Paper Type: Short

Research Area: Summarization

Research Area Keywords: incremental summarization, structured representation, prompting

Contribution Types: NLP engineering experiment

Languages Studied: english

Submission Number: 1824