# Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution

arXiv: https://arxiv.org/abs/2405.13095 · HTML: https://mlsanity.com/paper/2405.13095/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 21 May 2024.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [D2S: Document-to-Slide Generation Via Query-Based Text Summarization](https://mlsanity.com/paper/2105.03664/) (2021)
- [VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles](https://mlsanity.com/paper/2010.05406/) (2020)
- [On Learning Text Style Transfer with Direct Rewards](https://mlsanity.com/paper/2010.12771/) (2020)
- [Creating Suspenseful Stories: Iterative Planning with Large Language Models](https://mlsanity.com/paper/2402.17119/) (2024)
- [Automatically Generating Engaging Presentation Slide Decks](https://mlsanity.com/paper/1903.09308/) (2019)
- [Deep Submodular Networks for Extractive Data Summarization](https://mlsanity.com/paper/2010.08593/) (2020)

## Built on by (most cited first, 10 of 10)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation](https://mlsanity.com/paper/2502.05151/) (2025)
- [Scalable and Domain-General Abstractive Proposition Segmentation](https://mlsanity.com/paper/2406.19803/) (2024)
- [VideoAgent: Personalized Synthesis of Scientific Videos](https://mlsanity.com/paper/2509.11253/) (2025)
- [On Synthesizing Data for Context Attribution in Question Answering](https://mlsanity.com/paper/2504.05317/) (2025)
- [Taming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedback](https://mlsanity.com/paper/2505.18240/) (2025)
- [DeepSlide: From Artifacts to Presentation Delivery](https://mlsanity.com/paper/2605.15202/) (2026)
- [Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising](https://mlsanity.com/paper/2607.00407/) (2026)
- [InfoEdit: Probing Global Layout Reasoning in Infographic Editing](https://mlsanity.com/paper/2609.33286/) (2026)

## Abstract (arXiv)

Automatically generating a presentation from the text of a long document is a challenging and useful problem. In contrast to a flat summary, a presentation needs to have a better and non-linear narrative, i.e., the content of a slide can come from different and non-contiguous parts of the given document. However, it is difficult to incorporate such non-linear mapping of content to slides and ensure that the content is faithful to the document. LLMs are prone to hallucination and their performance degrades with the length of the input document. Towards this, we propose a novel graph based solution where we learn a graph from the input document and use a combination of graph neural network and LLM to generate a presentation with attribution of content for each slide. We conduct thorough experiments to show the merit of our approach compared to directly using LLMs for this task.