Automatically Generating Engaging Presentation Slide Decks
Not on the map. Why?
Abstract (arXiv)
Talented public speakers have thousands of hours of practice. One means of improving public speaking skills is practice through improvisation, e.g. presenting an improvised presentation using an unseen slide deck. We present TEDRIC, a novel system capable of generating coherent slide decks based on a single topic suggestion. It combines semantic word webs with text and image data sources to create an engaging slide deck with an overarching theme. We found that audience members perceived the quality of improvised presentations using these generated slide decks to be on par with presentations using human created slide decks for the Improvised TED Talk performance format. TEDRIC is thus a valuable new creative tool for improvisers to perform with, and for anyone looking to improve their presentation skills.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 4; 2025: 4.
9 papers.
- 2025AutoPresent: Designing Structured Visuals from Scratchcited by 63
- 2021D2S: Document-to-Slide Generation Via Query-Based Text Summarizationcited by 48
- 2024A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedianscited by 29
- 2024Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approachcited by 17
- 2024Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attributioncited by 10
- 2025Intent Tagging: Exploring Micro-Prompting Interactions for Supporting Granular Human-GenAI Co-Creation Workflowscited by 6
- 2025The Theater Stage as Laboratory: Review of Real-Time Comedy LLM Systems for Live Performancecited by 4
- 2024Designing and Evaluating Dialogue LLMs for Co-Creative Improvised Theatrecited by 1
- 2025Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesiscited by 1
- 2025Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis17 Jul 2025
- 2025Intent Tagging: Exploring Micro-Prompting Interactions for Supporting Granular Human-GenAI Co-Creation Workflows26 Feb 2025
- 2025The Theater Stage as Laboratory: Review of Real-Time Comedy LLM Systems for Live Performance14 Jan 2025
- 2025AutoPresent: Designing Structured Visuals from Scratch1 Jan 2025
- 2024Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach1 Jun 2024
- 2024A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians31 May 2024
- 2024Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attribution21 May 2024
- 2024Designing and Evaluating Dialogue LLMs for Co-Creative Improvised Theatre11 May 2024
- 2021D2S: Document-to-Slide Generation Via Query-Based Text Summarization8 May 2021