TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios

arXiv:2403.19318v1 Announce Type: new
Abstract: We introduce TableLLM, a robust large language model (LLM) with 13 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To …

abstract arxiv billion cs.cl data documents embedded enabling language language model large language large language model llm llms manipulation office parameters robust spreadsheets supervision tabular tabular data tasks training type usage world