WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
- URL: http://arxiv.org/abs/2503.19065v1
- Date: Mon, 24 Mar 2025 18:51:55 GMT
- Title: WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
- Authors: Zhongyu Yang, Jun Chen, Dannong Xu, Junjie Fei, Xiaoqian Shen, Liangbing Zhao, Chun-Mei Feng, Mohamed Elhoseiny,
- Abstract summary: We introduce WikiAutoGen, a novel system for automated multimodal Wikipedia-style article generation.<n>Unlike prior approaches, WikiAutoGen retrieves and integrates relevant images alongside text, enriching both the depth and visual appeal of generated content.<n>To further improve factual accuracy and comprehensiveness, we propose a multi-perspective self-reflection mechanism.
- Score: 29.386002986862568
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Knowledge discovery and collection are intelligence-intensive tasks that traditionally require significant human effort to ensure high-quality outputs. Recent research has explored multi-agent frameworks for automating Wikipedia-style article generation by retrieving and synthesizing information from the internet. However, these methods primarily focus on text-only generation, overlooking the importance of multimodal content in enhancing informativeness and engagement. In this work, we introduce WikiAutoGen, a novel system for automated multimodal Wikipedia-style article generation. Unlike prior approaches, WikiAutoGen retrieves and integrates relevant images alongside text, enriching both the depth and visual appeal of generated content. To further improve factual accuracy and comprehensiveness, we propose a multi-perspective self-reflection mechanism, which critically assesses retrieved content from diverse viewpoints to enhance reliability, breadth, and coherence, etc. Additionally, we introduce WikiSeek, a benchmark comprising Wikipedia articles with topics paired with both textual and image-based representations, designed to evaluate multimodal knowledge generation on more challenging topics. Experimental results show that WikiAutoGen outperforms previous methods by 8%-29% on our WikiSeek benchmark, producing more accurate, coherent, and visually enriched Wikipedia-style articles. We show some of our generated examples in https://wikiautogen.github.io/ .
Related papers
- WikiVideo: Article Generation from Multiple Videos [67.59430517160065]
We present the challenging task of automatically creating a high-level Wikipedia-style article that aggregates information from multiple videos about real-world events.
We introduce WikiVideo, a benchmark consisting of expert-written articles and densely annotated videos that provide evidence for articles' claims.
We propose Collaborative Article Generation (CAG), a novel interactive method for article creation from multiple videos.
arXiv Detail & Related papers (2025-04-01T16:22:15Z) - WeGen: A Unified Model for Interactive Multimodal Generation as We Chat [51.78489661490396]
We introduce WeGen, a model that unifies multimodal generation and understanding.<n>It can generate diverse results with high creativity for less detailed instructions.<n>We show it achieves state-of-the-art performance across various visual generation benchmarks.
arXiv Detail & Related papers (2025-03-03T02:50:07Z) - REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives [4.427603894929721]
This study proposes a novel approach to enhancing Wikipedia's B and C category biography articles.<n>By utilizing a multi-staged retrieval-augmented generation technique, we aim to enrich the informational content of lesser-known articles.
arXiv Detail & Related papers (2025-02-17T18:53:42Z) - WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario [32.28150998156827]
WIKIGENBENCH is a new benchmark consisting of 1,320 entries.<n>For generation, we explore a real-world scenario where structured, full-length Wikipedia articles with citations are generated for new events using input documents from web sources.<n>For evaluation, we integrate systematic metrics and LLM-based metrics to assess the verifiability, organization, and other aspects aligned with real-world scenarios.
arXiv Detail & Related papers (2024-02-28T11:51:56Z) - Automatic Quality Assessment of Wikipedia Articles -- A Systematic
Literature Review [0.8158530638728501]
We review existing methods for automatically measuring the quality of Wikipedia articles.
We identify and comparing machine learning algorithms, article features, quality metrics, and used datasets.
We hope that our analysis helps future researchers change that reality.
arXiv Detail & Related papers (2023-10-03T17:45:39Z) - WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions
from Paragraphs [66.88232442007062]
We introduce WikiDes, a dataset to generate short descriptions of Wikipedia articles.
The dataset consists of over 80k English samples on 6987 topics.
Our paper shows a practical impact on Wikipedia and Wikidata since there are thousands of missing descriptions.
arXiv Detail & Related papers (2022-09-27T01:28:02Z) - Surfer100: Generating Surveys From Web Resources on Wikipedia-style [49.23675182917996]
We show that recent advances in pretrained language modeling can be combined for a two-stage extractive and abstractive approach for Wikipedia lead paragraph generation.
We extend this approach to generate longer Wikipedia-style summaries with sections and examine how such methods struggle in this application through detailed studies with 100 reference human-collected surveys.
arXiv Detail & Related papers (2021-12-13T02:18:01Z) - Assessing the quality of sources in Wikidata across languages: a hybrid
approach [64.05097584373979]
We run a series of microtasks experiments to evaluate a large corpus of references, sampled from Wikidata triples with labels in several languages.
We use a consolidated, curated version of the crowdsourced assessments to train several machine learning models to scale up the analysis to the whole of Wikidata.
The findings help us ascertain the quality of references in Wikidata, and identify common challenges in defining and capturing the quality of user-generated multilingual structured data on the web.
arXiv Detail & Related papers (2021-09-20T10:06:46Z) - Wiki-Reliability: A Large Scale Dataset for Content Reliability on
Wikipedia [4.148821165759295]
We build the first dataset of English Wikipedia articles annotated with a wide set of content reliability issues.
To build this dataset, we rely on Wikipedia "templates"
We select the 10 most popular reliability-related templates on Wikipedia, and propose an effective method to label almost 1M samples of Wikipedia article revisions as positive or negative.
arXiv Detail & Related papers (2021-05-10T05:07:03Z) - Generating Wikipedia Article Sections from Diverse Data Sources [57.23574577984244]
We benchmark several training and decoding strategies on WikiTableT.
Our qualitative analysis shows that the best approaches can generate fluent and high quality texts but they sometimes struggle with coherence.
arXiv Detail & Related papers (2020-12-29T19:35:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.