Table Question Answering (TQA) presents a substantial challenge at the intersection of natural language processing and data analytics. This task involves answering natural language (NL) questions on top of tabular data, demanding proficiency in logical reasoning, understanding of data semantics, and fundamental analytical capabilities. Due to its significance, a substantial volume of research has been dedicated to exploring a wide range of strategies aimed at tackling this challenge including approaches that leverage Large Language Models (LLMs) through in-context learning or Chain-of-Thought (CoT) prompting as well as approaches that train and fine-tune custom models. Nonetheless, a conspicuous gap exists in the research landscape, where there is limited exploration of how innovative foundational research, which integrates incremental reasoning with external tools in the context of LLMs, as exemplified by the ReAct paradigm, could potentially bring advantages to the TQA task. In this paper, we aim to fill this gap, by introducing ReAcTable (ReAct for Table Question Answering tasks), a framework inspired by the ReAct paradigm that is carefully enhanced to address the challenges uniquely appearing in TQA tasks such as interpreting complex data semantics, dealing with errors generated by inconsistent data and generating intricate data transformations. ReAcTable relies on external tools such as SQL and Python code executors, to progressively enhance the data by generating intermediate data representations, ultimately transforming it into a more accessible format for answering the questions with greater ease. We demonstrate that ReAcTable achieves remarkable performance even when compared to fine-tuned approaches. In particular, it outperforms the best prior result on the WikiTQ benchmark, achieving an accuracy of 68.0% without requiring training a new model or fine-tuning.

翻译：表格问答（TQA）是自然语言处理与数据分析交叉领域的一项重大挑战。该任务涉及基于表格数据回答自然语言问题，要求具备逻辑推理能力、数据语义理解能力以及基础分析能力。由于其重要性，大量研究致力于探索多样策略以应对这一挑战，包括利用大型语言模型（LLM）通过上下文学习或思维链（CoT）提示的方法，以及训练和微调定制模型的方法。然而，研究领域存在一个显著空白：在LLM背景下，将增量推理与外部工具相结合的创新基础研究（如ReAct范式所体现的）对TQA任务可能带来的优势尚未得到充分探索。本文旨在填补这一空白，提出ReAcTable（面向表格问答任务的ReAct框架）。该框架受ReAct范式启发，并经过精心增强，以解决TQA任务中特有的挑战，例如解释复杂数据语义、处理不一致数据产生的错误以及生成复杂数据转换。ReAcTable依赖外部工具（如SQL和Python代码执行器），通过生成中间数据表示逐步增强数据，最终将其转换为更易于回答问题的格式。我们证明，即使与微调方法相比，ReAcTable也取得了显著性能。特别地，它在WikiTQ基准上以68.0%的准确率超越了先前最佳结果，且无需训练新模型或微调。