Research map / Vision-language and multimodal / Multimodal LLMs
WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
Zhongyu Yang, Jun Chen, Dannong Xu, Junjie Fei, Xiaoqian Shen, Liangbing Zhao, Chun-Mei Feng, Mohamed Elhoseiny
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-agent knowledge exploration (ablation) | WikiAutoGen · WikiSeek text quality, Image as Topic | average text score: 48.78 -> 66.56 | Improved |
| add outline proposal (ablation) | WikiAutoGen · WikiSeek text quality, Image as Topic | average text score: 48.78 -> 72.88 | Improved |
| add self-reflection (ablation) | WikiAutoGen · WikiSeek text quality, Image as Topic | average text score: 48.78 -> 71.60 | Improved |
| add multi-agent exploration on top of outline proposal + self-reflection (ablation) | WikiAutoGen · WikiSeek text quality, Image as Topic | average text score: 73.80 -> 77.49 | Improved |
| add self-reflection on top of outline proposal (ablation) | WikiAutoGen · WikiSeek text quality, Image as Topic | average text score: 72.88 -> 73.80 | Improved |
| add outline proposal on top of self-reflection (ablation) | WikiAutoGen · WikiSeek text quality, Image as Topic | average text score: 71.60 -> 73.80 | Improved |
| use WikiAutoGen instead of Co-Storm | WikiAutoGen · WikiSeek text quality, Text as Topic | average text score: 69.96 -> 78.73 | Improved |
| use WikiAutoGen instead of oRAG | WikiAutoGen · WikiSeek text quality, Image as Topic | average text score: 48.38 -> 77.49 | Improved |
| use WikiAutoGen instead of Co-Storm | WikiAutoGen · WikiSeek text quality, Image-Text as Topic | average text score: 63.77 -> 78.82 | Improved |
| use WikiAutoGen instead of oRAG | WikiAutoGen · WikiSeek image content, Text as Topic | average image score: 57.28 -> 68.99 | Improved |
| use WikiAutoGen instead of OmniThink | WikiAutoGen · WikiSeek image content, Image-Text as Topic | average image score: 55.25 -> 70.98 | Improved |
| use WikiAutoGen instead of OpenAI deep research | WikiAutoGen · WikiSeek, Prometheus2 judge, average | average score: 93.06 -> 89.01 | Hurt |
Closest papers by meaning
- A Dual-Way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking (AAAI 2024 · similarity 0.83)
- WikiSQE: A Large-Scale Dataset for Sentence Quality Estimation in Wikipedia (AAAI 2024 · similarity 0.82)
- Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs (CVPR 2026 · similarity 0.82)
- Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-Hoc Retrieval (AAAI 2024 · similarity 0.82)
- Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach (NeurIPS 2024 · similarity 0.81)
- Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs: Applying Large Language Models to Wikipedia and Linked Open Data (AAAI 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
