ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning
2026-06-01 • Information Retrieval
Information RetrievalArtificial IntelligenceComputation and LanguageMachine LearningMultiagent Systems
AI summaryⓘ
The authors noticed that current large language models (LLMs) struggle with predicting future numbers from tables, especially for tasks like forecasting real estate trends. They created a new task and dataset focused on time-series forecasting using real estate data. To tackle this, they developed TimeFore, a system with three parts: one that gets historical data using SQL, another that uses special forecasting models for better predictions, and a third that combines everything into clear answers. Their experiments show that TimeFore works well for these future prediction questions.
Large Language ModelsTabular Question AnsweringTime-Series ForecastingSQLReal Estate DataData RetrievalForecasting ModelsReasoningTimeForeData Synthesis
Authors
Zhensheng Wang, Xiaole Liu, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia
Abstract
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.