Research map / Large language models / Agents, code and math
TableMaster: A Recipe to Advance Table Understanding with Language Models
Lang Cao, Hanbing Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add textual reasoning (ablation) | TableMaster (gpt-4o-mini) · WikiTQ | accuracy (%): 73.85 -> 78.13 | Improved |
| add structure extraction (ablation) | TableMaster (gpt-4o-mini) · WikiTQ | accuracy (%): 74.75 -> 78.13 | Improved |
| add textual guidance to symbolic reasoning (ablation) | TableMaster (gpt-4o-mini) · WikiTQ | accuracy (%): 75.21 -> 78.13 | Improved |
| add table re-construction (ablation) | TableMaster (gpt-4o-mini) · WikiTQ | accuracy (%): 75.55 -> 78.13 | Improved |
| add table verbalization (ablation) | TableMaster (gpt-4o-mini) · WikiTQ | accuracy (%): 75.78 -> 78.13 | Improved |
| add table verbalization (ablation) | TableMaster (gpt-4o-mini) · TabFact | accuracy (%): 89.23 -> 90.12 | Improved |
| add column lookup (ablation) | TableMaster (gpt-4o-mini) · TabFact | accuracy (%): 90.51 vs 90.12 | No clear effect |
| add column lookup (ablation) | TableMaster (gpt-4o-mini) · WikiTQ | accuracy (%): 77.00 -> 78.13 | Improved |
| add symbolic reasoning (ablation) | TableMaster (gpt-4o-mini) · TabFact | accuracy (%): 89.18 -> 90.12 | Improved |
| add table of focus (ablation) | TableMaster (gpt-4o-mini) · WikiTQ | accuracy (%): 76.40 -> 78.13 | Improved |
| use TableMaster on top of GPT-4o-mini | gpt-4o-mini · FinQA | accuracy (%): 50.7 -> 66.4 | Improved |
| use TableMaster instead of end-to-end gpt-4o | gpt-4o · FetaQA | BLEU: 24.91 -> 28.94 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Chain-of-Table — Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding (ICLR 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding (ICLR 2024 · similarity 0.90)
- TableRAG: Million-Token Table Understanding with Language Models (NeurIPS 2024 · similarity 0.89)
- TableBench: A Comprehensive and Complex Benchmark for Table Question Answering (AAAI 2025 · similarity 0.89)
- OpenTab: Advancing Large Language Models as Open-domain Table Reasoners (ICLR 2024 · similarity 0.88)
- MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark (NeurIPS 2025 · similarity 0.88)
- NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
