Table QA

Table question answering asks how systems can answer natural-language questions over tables, spreadsheets, relational databases, and tables embedded in documents or images. Common approaches preserve structure with trees, graphs, or cell-level evidence; retrieve relevant regions; and combine language models with SQL or Python execution, sometimes through multi-agent planning. Benchmarks test lookup, aggregation, numerical reasoning, multi-hop questions, and visual or cross-modal understanding, and show persistent weaknesses on complex calculations and real-world tables. A central tension is that flexible language-model reasoning can be difficult to verify and sensitive to table format, while symbolic execution is more auditable but depends on accurate structure extraction and query translation.