Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document content, and reason over the collected evidence. Even advanced vision-language models (VLMs) can overlook sparse evidence and struggle with cross-modal reasoning in a single...
Zhuo-Wen Liang, Xiao-Tian Lin, Yu-Yu Luo et al.· 0 citations
DataMosaic is presented, an interactive system for constraint-driven document-to-database construction that incrementally builds entity and relationship tables through a closed loop of extraction, verification, repair, and targeted re-extraction.
Zhengxuan Zhang, Zhuo-Wen Liang, Hai-Xun Wang et al.· Proceedings of the VLDB Endo...· 2 citations
Doc2DB-Bench is introduced, a benchmark for Document-to-Database construction, containing 203 long-document instances across 42 schemas and seven domain groups, with 117 entity tables, 132 relationship tables, 7,341 rows, and 41,935 cells, which provides a testbed for reliable, auditable, and relationally faithful LLM-...
Zhuo-Wen Liang, Zhengxuan Zhang, Jia-Yang Wang et al.· 1 citation
DataSpace, a benchmark in which data agents produce verifiable tabular results from task-local heterogeneous workspaces, is introduced and key challenges for improving data-agent reliability are identified.
Boyan Li, Zhuo-Wen Liang, Yu-Peng Xie et al.· 1 citation
Experiments on public benchmarks and real-world industrial BI workloads show that QwenPaw-Data improves both verifiable data access capability and higher-level analytical quality, offering a practical foundation for reliable, traceable, and continuously improving enterprise data agents.
