作者位次 #3/5ACL 2026Findings· Findings of ACL
SMART : Semantic Header Flattening and Pseudo-Code-Style Reasoning for LLM -based Complex Table Question Answering
Yongshuo Zhang · Jixiong Chen · Kaihe xu · Wei Wei · Shihao Zou
摘要
Complex table question answering (TQA) remains challenging, as real-world table, usually designed for human readability with multi-level headers and fragmented hierarchical semantics, largely hindering large language models (LLMs) from accurately aligning conditions, attributes, and values during...