TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data

arXiv:2401.13223v2 Announce Type: replace
Abstract: In this work, we address question answering (QA) over a hybrid of tabular and textual data that are very common content on the Web (e.g. SEC filings), where discrete reasoning capabilities are often required. Recently, large language models (LLMs) like GPT-4 have demonstrated strong multi-step reasoning capabilities. We then consider harnessing the amazing power of LLMs to solve our task. We abstract a Step-wise Pipeline for tabular and textual QA, which consists of three key …

abstract arxiv capabilities cs.ai cs.cl data gpt gpt-4 hybrid language language model language models large language large language models llm llms question question answering reasoning sec tabular textual type web work