Answering numerical questions over hybrid contents from the given tables and text(TextTableQA) is a challenging task. Recently, Large Language Models (LLMs) have gained significant attention in the NLP community. With the emergence of large language models, In-Context Learning and Chain-of-Thought prompting have become two particularly popular research topics in this field. In this paper, we introduce a new prompting strategy called Hybrid prompt strategy and Retrieval of Thought for TextTableQA. Through In-Context Learning, we prompt the model to develop the ability of retrieval thinking when dealing with hybrid data. Our method achieves superior performance compared to the fully-supervised SOTA on the MultiHiertt dataset in the few-shot setting.

翻译：摘要：针对给定表格与文本的混合内容回答数值型问题（TextTableQA）是一项具有挑战性的任务。近年来，大型语言模型（LLMs）在自然语言处理领域获得了广泛关注。随着大型语言模型的出现，上下文学习（In-Context Learning）与思维链提示（Chain-of-Thought prompting）已成为该领域两个备受关注的研究热点。本文提出一种名为"混合提示策略与检索思考"（Hybrid prompt strategy and Retrieval of Thought）的新型提示方法，用于解决TextTableQA任务。通过上下文学习，我们引导模型在处理混合数据时发展检索思考能力。在MultiHiertt数据集的少样本设置下，本方法取得了优于全监督最先进模型（fully-supervised SOTA）的表现。