arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.09671cs.CL
收藏

在大语言模型时代表问题回答的综合调查:任务、方法和评估

Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation

Bosch Center for Artificial Intelligence, Renningen, Germany(博世人工智能研究中心,德国Renningen);LMU Munich & Munich Center for Machine Learning, Germany(慕尼黑大学 & 慕尼黑机器学习中心,德国);University of Augsburg, Germany(奥格斯堡大学,德国)

Wei Zhou, Bolei Ma, Annemarie Friedrich, Mohsen Mesgar

AI总结:

本文综述了表问题回答任务,探讨了基于大语言模型的方法,分析了现有基准和任务设置,并指出了未被系统覆盖的及时主题,为该领域提供了一个统一的基础。

摘要:

表问题回答(TQA)旨在回答关于表格数据的自然语言问题,通常伴随文本段落等附加上下文。该任务涵盖多样化的设置,差异体现在表格表示、问题/答案复杂性、涉及的模态和领域。尽管近期大语言模型(LLMs)的进展在TQA领域取得了显著进展,但该领域仍缺乏对任务公式化、核心挑战和方法学趋势的系统组织和理解,尤其是在强化学习等新兴研究方向下。本文通过提供全面且结构化的TQA研究概述,聚焦于基于LLM的方法。我们对现有基准和任务设置进行了全面分类,并根据它们所针对的挑战将当前的建模策略分组,分析其优缺点。此外,我们突出了尚未被系统覆盖但具有时效性的主题。通过统一分散的研究线索并识别开放问题,本文为TQA社区提供了一个整合的基础,使该领域能够更深入地理解当前最先进的状态,并指导该领域快速发展的未来研究。

英文摘要:

Table Question Answering (TQA) aims to answer natural language questions about tabular data, often accompanied by additional contexts such as text passages. The task spans diverse settings, varying in table representation, question/answer complexity, modality involved, and domain. While recent advances in large language models (LLMs) have led to substantial progress in TQA, the field still lacks a systematic organization and understanding of task formulations, core challenges, and methodological trends, particularly in light of emerging research directions such as reinforcement learning. This survey addresses this gap by providing a comprehensive and structured overview of TQA research with a focus on LLM-based methods. We provide a comprehensive categorization of existing benchmarks and task setups. We group current modeling strategies according to the challenges they target, and analyze their strengths and limitations. Furthermore, we highlight underexplored but timely topics that have not been systematically covered in prior research. By unifying disparate research threads and identifying open problems, our survey offers a consolidated foundation for the TQA community, enabling a deeper understanding of the state of the art and guiding future developments in this rapidly evolving area.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑