Summary of Enhancing Presentation Slide Generation by Llms with a Multi-staged End-to-end Approach, By Sambaran Bandyopadhyay et al.
Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach
by Sambaran Bandyopadhyay, Himanshu Maheshwari, Anandhavelu Natarajan, Apoorv Saxena
First submitted to arxiv on: 1 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach for generating presentation slides from long documents containing multimodal elements like text and images. The existing methods are often semi-automatic or only provide flat summaries, neglecting the importance of storytelling. In contrast, this research addresses the gap by developing a multi-staged end-to-end model that combines Large Language Models (LLMs) and Visual Language Models (VLMs). Experimental results demonstrate that this proposed solution outperforms applying LLMs directly with state-of-the-art prompting in terms of automated metrics and human evaluation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps create presentation slides from long documents. Usually, people do this manually, but it’s time-consuming and requires special knowledge. Other ways to make slides are only partially automatic or just give a brief summary without considering the importance of telling a story. This research finds a solution by creating a model that uses two types of artificial intelligence: language models and visual models. The results show that this approach is better than using language models alone in terms of how well it works automatically and how people evaluate it. |
Keywords
» Artificial intelligence » Prompting
