ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning
This work addresses the gap in LLM-based tabular QA for future-oriented numerical prediction, which is important for applications requiring time-series forecasting and reasoning.
The paper introduces a new task and dataset for open-domain tabular question answering focused on future data forecasting and reasoning, using real estate data. The proposed TimeFore framework, which combines retrieval, forecasting, and analysis, achieves improved accuracy over baselines.
The rapid development of LLMs has significantly advanced tabular question answering, but most systems cannot perform future-oriented numerical prediction. To address this gap, we introduce a novel task, Open-Domain Tabular Question Answering for Future Data Forecasting and Reasoning, and propose the first dataset to cover time-series forecasting and forecast-based reasoning scenarios using real estate data. This task poses challenges in retrieving precise historical data, overcoming the forecasting limitations of LLMs, and standardizing responses for diverse queries. To solve the above challenges, we propose TimeFore, an LLM agent-based framework that decomposes the problem into three collaborative roles: a Retriever autonomously generates SQL to fetch data, a Forecaster invokes external time-series models for higher accuracy, and an Analyzer synthesizes the results to construct a precise and consistent final answer. Extensive experiments demonstrate the effectiveness of our TimeFore.