17 citations · 25 across the 30 of their papers we have counts for
7 papers · 1 filter
Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction
Zhuowen Liang, Zhengxuan Zhang, Jiayang Wang +2
Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domains such as finance, healthcare,…
Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
Zhuowen Liang, Xiaotian Lin, Zhengxuan Zhang +3
Large language models (LLMs) are widely applied to data analytics over documents, yet direct reasoning over long, noisy documents remains brittle and error-prone. Hence, we study d…
TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
Bingheng Wu, Jingze Shi, Yifan Wu +2
Transformers exhibit proficiency in capturing long-range dependencies, whereas State Space Models (SSMs) facilitate linear-time sequence modeling. Notwithstanding their synergistic…
DataPuzzle: Breaking Free from the Hallucinated Promise of LLMs in Data Analysis
Zhengxuan Zhang, Zhuowen Liang, Yin Wu +3
Large language models (LLMs) are increasingly applied to multi-modal data analysis -- not necessarily because they offer the most precise answers, but because they provide fluent,…
SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph
Teng Lin, Yizhang Zhu, Yuyu Luo +1
Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple docu…
nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning
Tianqi Luo, Chuhan Huang, Leixian Shen +5
Text-to-Visualization (Text2VIS) enables users to create visualizations from natural language queries, making data insights more accessible. However, Text2VIS faces challenges in i…