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

TL;DR

This paper introduces a graph-based method combining graph neural networks and large language models to generate non-linear, faithful presentations from long documents, addressing hallucination and content attribution issues.

Contribution

It proposes a novel graph learning approach that enhances document-to-presentation transformation by capturing non-linear content relationships and improving content fidelity.

Findings

Outperforms direct LLM-based methods in presentation quality.

Effectively models non-linear content relationships.

Provides accurate attribution of content to slides.

Abstract

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.