ReAcTable: Enhancing ReAct for Table Question Answering
Summary: ReAcTable adapts the ReAct paradigm to TableQA, combining incremental reasoning with external SQL/Python executors to generate intermediate table representations that resolve complex semantics and noisy/inconsistent data. Evaluated on three TQA benchmarks, it yields SOTA-level results, improving WikiTQ to 68.0% (+2.1%) without fine-tuning. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yunjia Zhang (University of Wisconsin)
- 2. Jordan Henkel (Microsoft)
- 3. Avrilia Floratou (Microsoft)
- 4. Joyce Cahoon (Microsoft)
- 5. Shaleen Deep (Microsoft)
- 6. Jignesh M. Patel (Carnegie Mellon University)
BibTeX Citation
@article{zhang_vldb24,
title = {{ReAcTable: Enhancing ReAct for Table Question Answering}},
author = {Zhang, Yunjia and Henkel, Jordan and Floratou, Avrilia and Cahoon, Joyce and Deep, Shaleen and Patel, Jignesh M.},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {8},
pages = {1981--1994},
doi = {10.14778/3659437.3659452},
url = {https://doi.org/10.14778/3659437.3659452},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 16 of 16 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 950 | CAESURA: Language Models as Multi-Modal Query Planners | 2024 | CIDR | 0.0001302491 |
| 1,337 | DB-BERT: A Database Tuning Tool that "Reads the Manual" | 2022 | SIGMOD | 0.00011117488 |
| 2,298 | GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization | 2024 | VLDB | 8.7886538e-05 |
| 6,955 | DataChat: An Intuitive and Collaborative Data Analytics Platform | 2023 | SIGMOD | 5.7303405e-05 |
Previous
Page 1 / 1
Next