📢 New e-learning course!🔸 Practical, rights-based training for justice & child protection actors 📄 Self-paced | 🎓 Certificate on completion

👉https://justicewithchildren.org/en/learning/data-mosaic-e-learning-violence-against-children-detention #ChildRights #DataMOSAIC @tdhfoundation.bsky.social

Now live: the Data MOSAIC Tool — a practical resource for detention facilities to monitor #violence against #children.

📊 Incident-based reporting
📍 Pattern analysis
🧭 Rights-based guidance
💶Funded by the EU

🔗 justicewithchildren.org/en/news/data...

#ChildJustice #VAC #datamosaic

Zhengxuan Zhang, Zhuowen Liang, Yin Wu, Teng Lin, Yuyu Luo, Nan Tang
DataMosaic: Explainable and Verifiable Multi-Modal Data Analytics through Extract-Reason-Verify
https://arxiv.org/abs/2504.10036

downstream task requirements, enhancing consistency, completeness, and privacy. Through this approach, DataMosaic not only tackles the limitations of current LLM-powered analytics systems but also lays the groundwork for a new paradigm of grounded, [5/6 of https://arxiv.org/abs/2504.10036v1]

tables, graphs, trees) from raw data, DataMosaic provides transparent, step-by-step reasoning traces and enables validation of intermediate results. Built on a multi-agent framework, DataMosaic orchestrates self-adaptive agents that align with [4/6 of https://arxiv.org/abs/2504.10036v1]

noisy, inconsistent, or multi-modal data (for example, text, tables, images). We propose DataMosaic, a framework designed to make LLM-powered analytics both explainable and verifiable. By dynamically extracting task-specific structures (for example, [3/6 of https://arxiv.org/abs/2504.10036v1]

Zhengxuan Zhang, Zhuowen Liang, Yin Wu, Teng Lin, Yuyu Luo, Nan Tang: DataMosaic: Explainable and Verifiable Multi-Modal Data Analytics through Extract-Reason-Verify https://arxiv.org/abs/2504.10036 https://arxiv.org/pdf/2504.10036 https://arxiv.org/html/2504.10036