ACL Findings2026
Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions
Kun Zhou, Jiakai He, Wenmian Yang, Zhensheng Wang, Yiquan Zhang, Weijia Jia
Abstract
Presentation slides are a primary medium for data-driven reporting, yet keeping complex, analytics-style decks up to date remains laborintensive. Existing automation methods mostly follow fixed template filling and cannot support dynamic updates for diverse, user-authored slide decks. We therefore define "Dynamic Slide Update via Natural Language Instructions on User-provided Templates" and introduce DynaSlide, a large-scale benchmark with 20,036 real-world instruction-execution triples (source slide, user instruction, target slide) grounded in a shared external database and built from business reporting slides under bringyour-own-template (BYO-template) conditions. To tackle this task, we propose SlideAgent, an agent-based framework that combines multimodal slide parsing, natural language instruction grounding, and tool-augmented reasoning for tables, charts, and textual conclusions. SlideAgent updates content while preserving layout and style, providing a strong reference baseline on DynaSlide. We further design endto-end and component-level evaluation protocols that reveal key challenges and opportunities for future research. The dataset and code are available at https://github.com/XiaoZ hou2024/SlideAgent.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on10
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
- On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A SurveyLin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao et al.ACL Findings 2024 · 131 citations
- DOC2PPT: Automatic Presentation Slides Generation from Scientific DocumentsTsu-Jui Fu, William Yang Wang, Daniel McDuff, Yale SongAAAI 2022 · 83 citations
- Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment ClassificationLibo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni et al.AAAI 2021 · 77 citations
- Boosting Large Language Models with Continual Learning for Aspect-based Sentiment AnalysisXuanwen Ding, Jie Zhou, Liang Dou, Qin Chen et al.EMNLP Findings 2024 · 24 citations
Related papers
- Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data ManipulationKyudan Jung, Hojun Cho, Jooyeol Yun, Soyoung Yang et al.ACL Findings 2026
- SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document UnderstandingYiqiao Jin, Rachneet Kaur, Zhen Zeng, Sumitra Ganesh et al.ACL 2026 · 1 citation
- Design First, Code Later: Aesthetically Pleasing Template-Free Slides GenerationZhiyao Cui, Chenxu Wang, Shuyue Hu, Yiqun Zhang et al.ACL Findings 2026 · 3 citations
- SlideTailor: Personalized Presentation Slide Generation for Scientific PapersWenzheng Zeng, Mingyu Ouyang, Langyuan Cui, Hwee Tou NgAAAI 2026 · 3 citations
- DeepPresenter: Environment-Grounded Reflection for Agentic Presentation GenerationHao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan et al.ACL Findings 2026
