# Agentic LLMs for Question Answering over Tabular Data

Source: [Agentic LLMs for Question Answering over Tabular Data](<https://www.sota2.com/research/paper/68fa7b4c1e209131cea879fb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:37:33.682Z

Authors: Rishit Tyagi, Mohit Gupta, Rahul Bouri

Published: 2025-09-11T08:12:38.000Z

## Abstract

Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale, domain-diverse datasets to evaluate the ability of models to accurately answer structured queries. We propose a Natural Language to SQL (NL-to-SQL) approach leveraging large language models (LLMs) such as GPT-4o, GPT-4o-mini, and DeepSeek v2:16b to generate SQL queries dynamically. Our system follows a multi-stage pipeline involving example selection, SQL query generation, answer extraction, verification, and iterative refinement. Experiments demonstrate the effectiveness of our approach, achieving 70.5\\% accuracy on DataBench QA and 71.6\\% on DataBench Lite QA, significantly surpassing baseline scores of 26\\% and 27\\% respectively. This paper details our methodology, experimental results, and alternative approaches, providing insights into the strengths and limitations of LLM-driven Table QA.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.09234>)

[PDF](<https://arxiv.org/pdf/2509.09234.pdf>)