2 papers
cs.AI2026
Locating Failure in Multi-Page Visually Rich Document Understanding: An Empirical Attribution
Lewei Xu, Yihao Ding, Zihan Xu +5
Multi-page visually-rich document understanding (MP-VRDU) requires managing evidence that is sparse, spread across pages, and often exceeds a model's context window. Prior work has…
cs.DB2026
Disentangling Structure and Semantics: How Schema Representation Affects LLM-Based SQL Generation
Daniel Yitian Su, Sophie Yiran Su, Qiang Sun +2
LLM-based text-to-SQL pipelines read the database schema as text, which carries both structural cues (tables, keys, relationships) and semantic cues (table and column names); prior…