HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering
This work addresses a challenging task in NLP for table-text hybrid question answering, offering an incremental improvement through a novel prompting method.
The paper tackled the problem of answering numerical questions over hybrid table-text data by introducing a new prompting strategy called Hybrid prompt strategy and Retrieval of Thought (HRoT), which achieved superior performance compared to the fully-supervised state-of-the-art on the MultiHiertt dataset in a few-shot setting.
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.