Skip to content
conftrace_
2026 EMNLP EMNLP 2026

SIP: Aligning LLM-based TableQA with Table Semantics via SQL Logic

AbstractLarge 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.

More from EMNLP 2026

All EMNLP 2026 papers →