TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization
This addresses the challenge of multi-hop QA over tables and text without requiring labeled data, offering an incremental improvement in prompt-based approaches.
The paper tackled multi-hop table-text question answering by proposing a retrieval-augmented generation model with break-down prompting, achieving state-of-the-art performance for prompting-based methods using open-source LLMs like LLaMA3-70B.
Question answering (QA) over tables and text has gained much popularity over the years. Multi-hop table-text QA requires multiple hops between the table and text, making it a challenging QA task. Although several works have attempted to solve the table-text QA task, most involve training the models and requiring labeled data. In this paper, we have proposed a Retrieval Augmented Generation (RAG) based model - TTQA-RS: A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization. Our model uses an enhanced retriever for table-text information retrieval and uses augmented knowledge, including table-text summary with decomposed sub-questions with answers for a reasoning-based table-text QA. Using open-source language models, our model outperformed all existing prompting methods for table-text QA tasks on existing table-text QA datasets, such as HybridQA and OTT-QA's development set. Our experiments demonstrate the potential of prompt-based approaches using open-source LLMs. Additionally, by using LLaMA3-70B, our model achieved state-of-the-art performance for prompting-based methods on multi-hop table-text QA.