AixelAsk: A Stepwise-Guided Retrieval and Reasoning Framework for Large Table QA
Summary: Introduces AixelAsk, an LLM-based framework for large-table QA that constructs a DAG decomposition of execution nodes to guide stepwise LLM reasoning. Retrieves key rows/columns into sub-tables to cut tokens by ~86% while improving EM by 4–8%. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Chi Zhang (Beijing Institute of Technology)
- 2. Meihui Zhang (Beijing Institute of Technology)
- 3. Yuxin Yang (Beijing Institute of Technology)
- 4. Tao Chen (Beijing Institute of Technology)
- 5. Zhaojing Luo (Beijing Institute of Technology)
BibTeX Citation
@inproceedings{zhang_sigmod26,
title = {{AixelAsk: A Stepwise-Guided Retrieval and Reasoning Framework for Large Table QA}},
author = {Zhang, Chi and Zhang, Meihui and Yang, Yuxin and Chen, Tao and Luo, Zhaojing},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769831},
url = {https://dl.acm.org/doi/10.1145/3769831},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next