Challenges in Scalable TableQA
Table question answering with large language models remains difficult to scale: tables range from compact to million-token sizes, while questions require precise grounding of columns, values, and computations.
Limitations of Existing Methods
Existing methods often specialize in a fixed inference strategy, which is brittle across different table scales and model capabilities. Full-table reading is efficient for compact inputs but suffers from irrelevant context. Table reduction helps long inputs but depends on reliable evidence localization, while execution is required when tables exceed the model context window and remains sensitive to schema and value grounding errors.
TableRoute: Proposed Framework
We propose TableRoute, a capability-aware routing framework with evidence-conditioned inference for scalable TableQA.
TableRoute first generates validated question--table evidence and identifies the required operations, then routes each instance among these three strategies according to serialized table length and calibrated estimates of how reliably the base model handles these