Skip to content

Focus on Evidence: Relational-Structure Enhances LLM Effectiveness in TableQA

Sep 2026 · ACM Transactions on Information Systems · 0 citations · 71 references

TL;DR

EVA first extracts evidence-aware relational structures that associate question semantics with supporting table attributes that constraining sub-question generation within a grounded evidence space, and introduces relation-guided validation and integrates both DP and PyAgent reasoning to improve robustness across different reasoning patterns.

Abstract

Table Question Answering (TableQA) requires reasoning over natural language questions and structured tables, and remains challenging due to noisy evidence and complex multi-step reasoning. Recent Large Language Model (LLM)-based approaches typically adopt decomposition–reasoning–validation pipelines that combine Chain-of-Thought (CoT) decomposition, Direct Prompting (DP), Python Agent (PyAgent) execution, and self-validation. However, these methods still largely rely on unconstrained LLM reasoning during decomposition, which may introduce unsupported sub-questions and irrelevant evidence expansion. We propose EVidence-Aware (EVA), a framework that explicitly grounds decomposition on question-relevant table evidence before reasoning begins. EVA first extracts evidence-aware relational structures that associate question semantics with supporting table attributes, thereby constraining sub-question generation within a grounded evidence space. EVA further introduces relation-guided validation and integrates both DP and PyAgent reasoning to improve robustness across different reasoning patterns. Experiments on datasets across multiple LLMs demonstrate that EVA consistently improves reasoning reliability and achieves strong performance across diverse TableQA settings.

View source

Similar papers

Preprint Aug 2026

PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding

PARTAB (Partition-Aware Reasoning overTables), a framework that constructs a structured evidence interface between the LLM and the table, demonstrates the value of structured, partition aware evidence construction for scalable table reasoning.

Md Mahadi Hasan Nahid, Davood Rafiei · 0 citations
2026

Reasoning Graph-Structured Question Answering: Datasets and Insights from LLM Benchmarking

GRS-QA is introduced, a reasoning graph-structured question answering dataset that augments multi-hop QA instances from exisiting datasets, with directed reasoning graphs representing intermediate inference steps, and highlights the importance of unified structural annotations for understanding and improving multi-hop...

Khin S. Yone, Devasha Trivedi, Anish Pahilajani et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updatable factual grounding, making them a promising external knowledge sou...

Yang Hong, Ya-Jun Yang, Xin Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents

This work introduces DocHop, a benchmark for integrated chart--context reasoning in document-style images and constructs DocHop via a stochastic logic-first generation pipeline with controllable reasoning depth and visual density, to enable systematic evaluation.

Zhuo-Ran Yu, Le Thien Phuc Nguyen, Jaden Park et al. · 1 citation
Open access Oct 2026

Dynamic path reasoning with large language models for interpretable knowledge graph question answering

Knowledge graph question answering (KGQA) aims to answer natural language questions by grounding them in structured knowledge graphs (KGs). Current KGQA systems still face three linked challenges: representing complex and compositional questions, providing transparent multi-hop reasoning traces, and using complete...

Ling-Wang Yuan, Bi-Cheng Wu, Yang-Yang-Er-Er-Er-Hong-Hong-Hong Yang · 0 citations
#artificial intelligence Preprint Sep 2026

TabScope: Question-Adaptive Scope Selection for Table Question Answering

Experiments on WikiTQ and SLQA show that localization is particularly effective for lookup and local reasoning questions, while adaptive selection between localized and full-table reasoning achieves the best overall performance, highlighting that long-table QA requires deciding not only how to localize, but also when t...

Yu-Xiang Wang, Jun-Hao Gan, Jian-Zhong Qi · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.