# Enhancing Incremental Summarization with Structured Representations

arXiv: https://arxiv.org/abs/2407.15021 · HTML: https://mlsanity.com/paper/2407.15021/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 21 Jul 2024.

## Builds on (most cited first, 9 of 9)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability](https://mlsanity.com/paper/2402.18667/) (2024)
- [STRUM-LLM: Attributed and Structured Contrastive Summarization](https://mlsanity.com/paper/2403.19710/) (2024)
- [SUMIE: A Synthetic Benchmark for Incremental Entity Summarization](https://mlsanity.com/paper/2406.05079/) (2024)

## Built on by (most cited first, 4 of 4)

- [PRISM: Efficient Long-Range Reasoning With Short-Context LLMs](https://mlsanity.com/paper/2412.18914/) (2024)
- [VeriTrail: Closed-Domain Hallucination Detection with Traceability](https://mlsanity.com/paper/2505.21786/) (2025)
- [Detect, Remask, Repair: Diffusion Editing for Faithful Summarization of Evolving Contexts](https://mlsanity.com/paper/2606.12807/) (2026)
- [Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization](https://mlsanity.com/paper/2608.09043/) (2026)

## Abstract (arXiv)

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 (GUjson), which significantly improve summarization performance by 40% and 14% across two public datasets. Most notably, we propose the Chain-of-Key strategy (CoKjson) 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.