Causality Meets the Table: Debiasing LLMs for Faithful TableQA via Front-Door Intervention

Zhen Yang (Beijing University of Technology) · Ziwei Du (Anhui University) · Minghan Zhang (Anhui University) · Wei Du (Shandong University) · Jie Chen (Hong Kong Baptist University) · Fulan Qian (Anhui University) · Shu Zhao (Anhui University)

agent paradigmscausal intervention confoundersdirect promptingfront-door adjustment logical inference natural language understanding overfittingquestion variant generationsemantic interpretationspurious correlationsstructural causal graphstructured data reasoningtable question answering

Table Question Answering (TableQA) combines natural language understanding and structured data reasoning, posing challenges in semantic interpretation and logical inference. Recent advances in Large Language Models (LLMs) have improved TableQA performance through Direct Prompting and Agent paradigms. However, these models often rely on spurious correlations, as they tend to overfit to token co-occurrence patterns in pretraining corpora, rather than perform genuine reasoning. To address this issue, we propose Causal Intervention TableQA (CIT), which is based on a structural causal graph and applies front-door adjustment to eliminate bias caused by token co-occurrence. CIT formalizes TableQA as a causal graph and identifies token co-occurrence patterns as confounders. By applying front-door adjustment, CIT guides question variant generation and reasoning to reduce confounding effects. Experiments on multiple benchmarks show that CIT achieves state-of-the-art performance, demonstrating its effectiveness in mitigating bias. Consistent gains across various LLMs further confirm its generalizability.