| ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics | | 80.8 | | | | ARTEMIS-DA | 2024-12-18 |
| Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering | ✓ Link | 76.6 | / | | | TabLaP | 2024-10-10 |
| SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA | ✓ Link | 74.4 | | 65.2 | | SynTQA (GPT) | 2024-09-25 |
| Rethinking Tabular Data Understanding with Large Language Models | ✓ Link | 73.6 | / | | | Mix SC | 2023-12-27 |
| SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA | ✓ Link | 71.6 | / | | | SynTQA (RF) | 2024-09-25 |
| CABINET: Content Relevance based Noise Reduction for Table Question Answering | ✓ Link | 69.1 | / | | | CABINET | 2024-02-02 |
| NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization | ✓ Link | 68.63 | | | | NormTab+TabSQLify | 2024-06-25 |
| Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding | ✓ Link | 67.31 | / | | | Chain-of-Table | 2024-01-09 |
| Efficient Prompting for LLM-based Generative Internet of Things | | 66.78 | / | | | Tab-PoT | 2024-06-14 |
| Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning | ✓ Link | 65.9 | 64.8 | | | Dater | 2023-01-31 |
| LEVER: Learning to Verify Language-to-Code Generation with Execution | ✓ Link | 65.8 | 64.6 | | | LEVER | 2023-02-16 |
| TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition | ✓ Link | 64.7 | | | | TabSQLify (col+row) | 2024-04-15 |
| Binding Language Models in Symbolic Languages | ✓ Link | 64.6 | 65.0 | | | Binder | 2022-10-06 |
| OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering | ✓ Link | 63.3 | 62.5 | | | OmniTab-Large | 2022-07-08 |
| NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization | ✓ Link | 61.20 | | | | NormTab (Targeted) + SQL | 2024-06-25 |
| ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples | ✓ Link | 58.7 | 59.7 | | | ReasTAP-Large | 2022-10-22 |
| TAPEX: Table Pre-training via Learning a Neural SQL Executor | ✓ Link | 57.5 | 57.0 | | | TAPEX-Large | 2021-07-16 |
| TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data | ✓ Link | 51.8 | 52.2 | | | MAPO + TABERTLarge (K = 3) | 2020-05-17 |
| UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models | ✓ Link | 49.29 | 50.65 | | | T5-3b(UnifiedSKG) | 2022-01-16 |
| TAPAS: Weakly Supervised Table Parsing via Pre-training | ✓ Link | 48.8 | / | | | TAPAS-Large (pre-trained on SQA) | 2020-04-05 |
| Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs | ✓ Link | 44.5 | 43.7 | | | Structured Attention | 2019-09-09 |
| SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA | ✓ Link | | | | 77.5 | SynTQA (Oracle) | 2024-09-25 |