@inproceedings{yang-etal-2026-sip,
title = "{SIP}: Aligning {LLM}-based {T}able{QA} with Table Semantics via {SQL} Logic",
author = "Yang, Zhen and
Du, Ziwei and
Zhang, Minghan and
Du, Wei and
Zou, Haodong and
Tan, Shicheng and
Chen, Jie and
Zhao, Shu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1947/",
pages = "44287--44299",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) have achieved strong performance on Table Question Answering (TableQA), yet their reasoning processes often remain misaligned with the underlying table semantics. This misalignment can lead to decompositions and validation steps that fail to faithfully capture the table operations required by the question. In this paper, we introduce SIP, a SQL Logic-aligned framework for improving the semantic consistency of LLM-based table reasoning. SIP is built around SQL Logic, a natural-language abstraction of standard SQL operators that explicitly represents operations such as projection, filtering, ordering, and aggregation while avoiding the syntactic brittleness of executable SQL. SQL Logic serves as a shared operator-level representation that guides sub-question decomposition and supports operator-aware validation in both Direct Prompting and Python Agent settings. Experiments on three TableQA benchmarks show that SIP achieves state-of-the-art performance and consistently improves robustness across diverse LLMs, demonstrating the value of explicit semantic representations for structured table reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-sip">
<titleInfo>
<title>SIP: Aligning LLM-based TableQA with Table Semantics via SQL Logic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haodong</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shicheng</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have achieved strong performance on Table Question Answering (TableQA), yet their reasoning processes often remain misaligned with the underlying table semantics. This misalignment can lead to decompositions and validation steps that fail to faithfully capture the table operations required by the question. In this paper, we introduce SIP, a SQL Logic-aligned framework for improving the semantic consistency of LLM-based table reasoning. SIP is built around SQL Logic, a natural-language abstraction of standard SQL operators that explicitly represents operations such as projection, filtering, ordering, and aggregation while avoiding the syntactic brittleness of executable SQL. SQL Logic serves as a shared operator-level representation that guides sub-question decomposition and supports operator-aware validation in both Direct Prompting and Python Agent settings. Experiments on three TableQA benchmarks show that SIP achieves state-of-the-art performance and consistently improves robustness across diverse LLMs, demonstrating the value of explicit semantic representations for structured table reasoning.</abstract>
<identifier type="citekey">yang-etal-2026-sip</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1947/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>44287</start>
<end>44299</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SIP: Aligning LLM-based TableQA with Table Semantics via SQL Logic
%A Yang, Zhen
%A Du, Ziwei
%A Zhang, Minghan
%A Du, Wei
%A Zou, Haodong
%A Tan, Shicheng
%A Chen, Jie
%A Zhao, Shu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yang-etal-2026-sip
%X Large Language Models (LLMs) have achieved strong performance on Table Question Answering (TableQA), yet their reasoning processes often remain misaligned with the underlying table semantics. This misalignment can lead to decompositions and validation steps that fail to faithfully capture the table operations required by the question. In this paper, we introduce SIP, a SQL Logic-aligned framework for improving the semantic consistency of LLM-based table reasoning. SIP is built around SQL Logic, a natural-language abstraction of standard SQL operators that explicitly represents operations such as projection, filtering, ordering, and aggregation while avoiding the syntactic brittleness of executable SQL. SQL Logic serves as a shared operator-level representation that guides sub-question decomposition and supports operator-aware validation in both Direct Prompting and Python Agent settings. Experiments on three TableQA benchmarks show that SIP achieves state-of-the-art performance and consistently improves robustness across diverse LLMs, demonstrating the value of explicit semantic representations for structured table reasoning.
%U https://aclanthology.org/2026.emnlp-main.1947/
%P 44287-44299
Markdown (Informal)
[SIP: Aligning LLM-based TableQA with Table Semantics via SQL Logic](https://aclanthology.org/2026.emnlp-main.1947/) (Yang et al., EMNLP 2026)
ACL
- Zhen Yang, Ziwei Du, Minghan Zhang, Wei Du, Haodong Zou, Shicheng Tan, Jie Chen, and Shu Zhao. 2026. SIP: Aligning LLM-based TableQA with Table Semantics via SQL Logic. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 44287–44299, Budapest, Hungary. Association for Computational Linguistics.