# Structsum Generation for Faster Text Comprehension

arXiv: https://arxiv.org/abs/2401.06837 · HTML: https://mlsanity.com/paper/2401.06837/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 12 Jan 2024.

## Builds on (most cited first, 27 of 27)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [UL2: Unifying Language Learning Paradigms](https://mlsanity.com/paper/2205.05131/) (2022)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Neural Summarization by Extracting Sentences and Words](https://mlsanity.com/paper/1603.07252/) (2016)
- [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://mlsanity.com/paper/2212.08037/) (2022)
- [Shepherd: A Critic for Language Model Generation](https://mlsanity.com/paper/2308.04592/) (2023)
- [Successive Prompting for Decomposing Complex Questions](https://mlsanity.com/paper/2212.04092/) (2022)
- [Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary](https://mlsanity.com/paper/2010.00490/) (2020)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [Global Reasoning over Database Structures for Text-to-SQL Parsing](https://mlsanity.com/paper/1908.11214/) (2019)
- [Data-to-text Generation with Macro Planning](https://mlsanity.com/paper/2102.02723/) (2021)
- [Table-To-Text generation and pre-training with TabT5](https://mlsanity.com/paper/2210.09162/) (2022)
- [A Sequence-to-Sequence&Set Model for Text-to-Table Generation](https://mlsanity.com/paper/2306.00137/) (2023)
- [STable: Table Generation Framework for Encoder-Decoder Models](https://mlsanity.com/paper/2206.04045/) (2022)
- [Scalable Micro-planned Generation of Discourse from Structured Data](https://mlsanity.com/paper/1810.02889/) (2018)
- [Unified Text Structuralization with Instruction-tuned Language Models](https://mlsanity.com/paper/2303.14956/) (2023)
- [Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement](https://mlsanity.com/paper/2109.02457/) (2021)

## Built on by (most cited first, 9 of 9)

- [StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization](https://mlsanity.com/paper/2410.08815/) (2024)
- [Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction](https://mlsanity.com/paper/2404.14215/) (2024)
- [Map&Make: Schema Guided Text to Table Generation](https://mlsanity.com/paper/2505.23174/) (2025)
- [SQUiD: Synthesizing Relational Databases from Unstructured Text](https://mlsanity.com/paper/2505.19025/) (2025)
- [Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval](https://mlsanity.com/paper/2601.16462/) (2026)
- [Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework](https://mlsanity.com/paper/2508.12257/) (2025)
- [LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement](https://mlsanity.com/paper/2508.08653/) (2025)
- [Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives](https://mlsanity.com/paper/2510.18173/) (2025)
- [Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction](https://mlsanity.com/paper/2608.08459/) (2026)

## Abstract (arXiv)

We consider the task of generating structured representations of text using large language models (LLMs). We focus on tables and mind maps as representative modalities. Tables are more organized way of representing data, while mind maps provide a visually dynamic and flexible approach, particularly suitable for sparse content. Despite the effectiveness of LLMs on different tasks, we show that current models struggle with generating structured outputs. In response, we present effective prompting strategies for both of these tasks. We introduce a taxonomy of problems around factuality, global and local structure, common to both modalities and propose a set of critiques to tackle these issues resulting in an absolute improvement in accuracy of +37pp (79%) for mind maps and +15pp (78%) for tables. To evaluate semantic coverage of generated structured representations we propose Auto-QA, and we verify the adequacy of Auto-QA using SQuAD dataset. We further evaluate the usefulness of structured representations via a text comprehension user study. The results show a significant reduction in comprehension time compared to text when using table (42.9%) and mind map (31.9%), without loss in accuracy.