大语言模型是复杂表格解析器
Large Language Models are Complex Table Parsers
AI总结：
针对现有GPT相关问答研究忽略复杂表格问答挑战的问题，本文提出将复杂表格重构为元组并优化提示模板的方法，增强GPT-3.5的层级结构感知能力，在HiTAB和AIT-QA数据集上均取得SOTA性能。
摘要：
随着生成式预训练Transformer 3.5（GPT-3.5）在自然语言处理（NLP）领域展现出卓越的推理与理解能力，大多数问答（QA）研究主要围绕基于GPT的通用问答任务展开，却忽略了复杂表格问答带来的特定挑战。本文提出引入GPT-3.5来应对这类挑战，具体做法是将复杂表格重构为元组，并针对对话设计特定提示词。具体而言，我们将每个单元格的层级结构、位置信息和内容编码为一个元组。通过在提示模板中补充每个元组含义的解释性描述以及任务的逻辑推理过程，我们有效提升了GPT-3.5的层级结构感知能力，使其能更好地解析复杂表格。在复杂表格问答数据集（即开放域数据集HiTAB和航空领域数据集AIT-QA）上开展的大量实验及结果表明，我们的方法在两个数据集上均显著优于此前的研究工作，取得了当前最优（SOTA）性能。
英文摘要：
With the Generative Pre-trained Transformer 3.5 (GPT-3.5) exhibiting remarkable reasoning and comprehension abilities in Natural Language Processing (NLP), most Question Answering (QA) research has primarily centered around general QA tasks based on GPT, neglecting the specific challenges posed by Complex Table QA. In this paper, we propose to incorporate GPT-3.5 to address such challenges, in which complex tables are reconstructed into tuples and specific prompt designs are employed for dialogues. Specifically, we encode each cell's hierarchical structure, position information, and content as a tuple. By enhancing the prompt template with an explanatory description of the meaning of each tuple and the logical reasoning process of the task, we effectively improve the hierarchical structure awareness capability of GPT-3.5 to better parse the complex tables. Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets, leading to state-of-the-art (SOTA) performance.
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。
