ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification

2026-04-11

AI Summary

This work addresses the challenge of handling ambiguous or uncertain queries in open-domain table question answering (TQA) with large language models. To this end, the authors propose MAIC-TQA, a multi-agent interactive clarification framework, and introduce ODUTQA-MDC—the first comprehensive benchmark specifically designed for this task. ODUTQA-MDC comprises 209 tables and 25,105 fine-grained annotated question-answer pairs, enabling multi-turn conversational clarification and simulating dynamic user feedback. Experimental results demonstrate that MAIC-TQA substantially outperforms existing approaches in ambiguity detection and intent clarification, establishing a new paradigm and providing essential resources for research on interactive, ambiguity-aware table question answering.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Intelligent Query Processing
• Multiagent Systems: Multiagent Systems under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Community question answering

Abstract

The advancement of large language models (LLMs) has enhanced tabular question answering (Tabular QA), yet they struggle with open-domain queries exhibiting underspecified or uncertain expressions. To address this, we introduce the ODUTQA-MDC task and the first comprehensive benchmark to tackle it. This benchmark includes: (1) a large-scale ODUTQA dataset with 209 tables and 25,105 QA pairs; (2) a fine-grained labeling scheme for detailed evaluation; and (3) a dynamic clarification interface that simulates user feedback for interactive assessment. We also propose MAIC-TQA, a multi-agent framework that excels at detecting ambiguities, clarifying them through dialogue, and refining answers. Experiments validate our benchmark and framework, establishing them as a key resource for advancing conversational, underspecification-aware Tabular QA research.

Problem

• open-domain
• underspecified
• tabular question answering
• multi-turn dialogue
• clarification

Innovation

• Open-Domain Tabular QA
• Underspecified Questions
• Multi-turn Dialogue Clarification
• Multi-agent Framework
• Dynamic Clarification Interface