TableRoute: Capability-Aware Routing for Scalable Table Question Answering
Organizations: The University of Melbourne
Abstract
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. 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. 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 operations. The validated evidence supports the selected route by grounding columns, values, and conditions. Across WikiTQ, WTQ-L, BirdQA, and TableBench, TableRoute consistently improves accuracy through complementary routing and evidence conditioning across table scales, while reducing online token cost. Code will be made available upon publication.
Figures & tables
| Error Type | Short | Long | Massive | Overall |
| Semantic mismatch | 44.0 | 31.0 | 52.0 | 42.3 |
| Computation error | 24.0 | 28.0 | – | 17.4 |
| Evidence localization | 17.0 | 26.0 | – | 14.3 |
| Reduction or execution error | 7.0 | 11.0 | 41.0 | 19.7 |
| Others | 8.0 | 4.0 | 7.0 | 6.3 |
| Semantic + computation | 68.0 | 59.0 | 52.0 | 59.7 |
| Strategy | WTQ-L | BirdQA | ||
| Acc. | Relative Cost ( ) | Acc. | Relative Cost ( ) | |
| CoT only | 58.1 | 1.00 | – | – |
| DATER only | 54.7 | 3.15 | 61.8 | 2.76 |
| DeepEye-SQL only | – | – | 69.7 | 1.00 |
| LLM Self-routing | 60.4 | 1.48 | 66.8 | 1.34 |
| Answer Selection | 62.0 | 4.15 | 69.0 | 3.76 |
| Computation Type | #Q | CoT | TableRoute | |
| Count | 1704 | 73.7 | 74.8 | +1.1 |
| Diff. | 103 | 65.0 | 68.9 | +3.9 |
| Sum | 105 | 78.1 | 80.0 | +1.9 |
| Avg. | 23 | 56.5 | 65.2 | +8.7 |
| Extrema | 85 | 72.9 | 76.5 | +3.6 |
| Ratio | 11 | 63.6 | 72.7 | +9.1 |
| (a) Components and fixed routes | |||
| Setting | WikiTQ | WTQ-L | BirdQA |
| TableRoute | 78.8 | 67.6 | 75.7 |
| w/o Validated Evidence | 76.3 ( 2.5) | 63.8 ( 3.8) | 70.8 ( 4.9) |
| w/o Computational Support | 76.8 ( 2.0) | 65.5 ( 2.1) | – |
| Direct -only | 75.2 ( 3.6) | 41.0 ( 26.6) | – |
| Reduce -only | 73.8 ( 5.0) | 61.3 ( 6.3) | – |
Appendix figures & tables21 assets
Supplementary material from the paper’s appendix.
Appendix
| Method | Direct QA | Table Reduction | Program Execution | Pre-exec. Routing | Single-route Inference | Validated Evidence | Model-specific Boundary |
| Binder | ✗ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ |
| Dater | ✗ | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ |
| Chain-of-Table | ✗ | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ |
| SynTQA | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ |
| TableRAG | ✗ | ✓ | ✓ | ✗ | ✗ | ✗ | ✗ |
| TALON | ✗ | ✓ | ✓ | ✗ | ✗ | ✗ | ✗ |
| Method | Acc. |
| Bird ( Li et al., 2023 ) | 55.8 |
| DAIL-SQL ( Gao et al., 2024 ) | 54.8 |
| TA-SQL ( Qu et al., 2024 ) | 56.1 |
| MAC-SQL ( Wang et al., 2025a ) | 59.6 |
| DeepEye-SQL ( Li et al., 2026 ) | 69.7 |
| Field | Description |
| semantic_unit | Question phrase to be grounded. |
| column_hint | Natural-language hint for the target column. |
| grounding_type | Expected value type: text , number , or date . |
| operator | Condition operator. |
| value | Main literal value. |
| value2 | Second value for between ; empty otherwise. |
| Dataset | Avg cand. | Kept | Dropped | Empty |
| WikiTQ | 1.872 | 0.736 | 0.264 | 30.1% |
| WTQ-L | 1.773 | 0.811 | 0.189 | 15.5% |
| Failure type | WikiTQ | WTQ-L |
| Unresolved column | 1180 / 8132 | 56 / 596 |
| Type mismatch | 105 / 8132 | 14 / 596 |
| Parse failure | 600 / 8132 | 34 / 596 |
| Not executable | 971 / 8132 | 57 / 596 |
| Model | Short | Medium | Long |
| Qwen | 0.750 | 0.656 | 0.617 |
| GPT | 0.796 | 0.722 | 0.642 |
| LLaMA | 0.740 | 0.644 | 0.658 |
| Avg. | 0.763 | 0.674 | 0.639 |
| Operation | Acc. | |
| Projection | 0.736 | 1,214 |
| Sort | 0.729 | 380 |
| Top-k | 0.726 | 357 |
| Neighbor | 0.720 | 214 |
| Filter | 0.686 | 948 |
| Compute | 0.686 | 102 |
| Operation | Short | Long | |
| Projection | 0.785 | 0.687 | -0.098 |
| Filter | 0.779 | 0.610 | -0.169 |
| Neighbor | 0.763 | 0.691 | -0.072 |
| Sort | 0.781 | 0.648 | -0.133 |
| Top-k | 0.793 | 0.612 | -0.181 |
| Aggregate | 0.747 | 0.449 | -0.298 |
| Group | Operation types |
| Light | Projection , Filter , Neighbor |
| Heavy | Sort , TopK , Aggregate , Compute |
| Setting | Symbol | Default |
| Reference table size | 2,048 | |
| Accuracy tolerance | 0.10 | |
| Initial bin width | – | 256 |
| Minimum bin size | 50 | |
| One-sided tail | 0.05 |
| Model | Light range | Heavy range | ||
| GPT | 0.796 | 0.696 | ||
| LLaMA | 0.740 | 0.640 | ||
| Qwen | 0.752 | 0.652 |
| Model | Calibration | Dir. | Red. | Exec. |
| GPT | Model-only | 48.81 | 42.56 | 8.63 |
| GPT | Model+Group | 44.35 | 47.02 | 8.63 |
| LLaMA | Model-only | 41.97 | 49.40 | 8.63 |
| LLaMA | Model+Group | 40.48 | 50.89 | 8.63 |
| Qwen | Model-only | 46.73 | 44.64 | 8.63 |
| Qwen | Model+Group | 38.99 | 52.38 | 8.63 |
| Routing Strategy | WikiTQ | WTQ-L |
| Length-only | 81.7 | 68.5 |
| LLM-based | 82.0 | 68.8 |
| Learned | 82.2 | 69.0 |
| TableRoute | 82.5 | 69.6 |
| Setting | WikiTQ | WTQ-L |
| Original three backbones (average) | ||
| Model-specific calibration | 78.8 | 67.6 |
| Cross-model calibration | 78.6 | 67.3 |
| LLM semantic routing | 79.0 | 68.6 |
| GPT-5-mini | ||
| Per-operation calibration | 82.4 | 69.4 |
| Setting | Acc. |
| Schema-only reduction | 66.5 |
| Schema-only reduction + evidence | 68.0 |
| Best schema-only reduction | 70.1 |
| Full-table-visible reduction | 70.9 |
| Dataset | #Q | Min Rows | Max Rows | Min Cols | Max Cols | Avg. Tokens |
| WikiTQ | 4,344 | 5 | 517 | 3 | 21 | 842.6 |
| WTQ-L | 336 | 49 | 517 | 3 | 11 | 3,819.0 |
| TableBench | 828 | 6 | 176 | 4 | 20 | 512.8 |
| BirdQA | 314 | 25 | 1,056,320 | 2 | 74 | 5,669,661.2 |
| Method | GPT-4o-mini | Qwen2.5-72B | ||
| End-to-End QA | 56.4 | 54.2 | 36.1 | 25.0 |
| Python QA | 52.1 | 55.6 | 34.6 | 35.4 |
| Binder | 58.5 | 60.6 | 58.5 | 58.5 |
| Dater | 53.7 | 52.8 | 52.4 | 45.3 |
| RowColRetrieval | 47.6 | 50.0 | 48.7 | 50.0 |
| Base LLM | CoT | RoT | TableRoute |
| LLaMA3.3-70B | 38.2 | 44.8 | 48.7 |
| Operator | Pseudo-code |
| projection | Function Projection : |
| verify all columns exist in | |
| return | |
| filter | Function Filter : |
| evaluate each column--operator--value condition |
| Method | WikiTQ | WTQ-L | BirdQA |
| CoT ( Wei et al., 2022 ) | 76.4 | 55.9 | – |
| RoT ( Zhang et al., 2025 ) | 81.7 | 56.5 | – |
| TALON ( Jin et al., 2025 ) | 71.9 | 67.9 | 72.6 |
| TableRoute | 82.5 | 69.6 | 76.1 |
| +0.8 | +1.7 | +3.5 |
Table QA
Table question answering studies how AI systems retrieve, interpret, and reason over structured data to answer natural-language questions.
See all 70 papers