TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913693579608064 |
|---|---|
| author | Zhang, Xiaokang Luo, Sijia Zhang, Bohan Ma, Zeyao Zhang, Jing Li, Yang Li, Guanlin Yao, Zijun Xu, Kangli Zhou, Jinchang Zhang-Li, Daniel Yu, Jifan Zhao, Shu Li, Juanzi Tang, Jie |
| author_facet | Zhang, Xiaokang Luo, Sijia Zhang, Bohan Ma, Zeyao Zhang, Jing Li, Yang Li, Guanlin Yao, Zijun Xu, Kangli Zhou, Jinchang Zhang-Li, Daniel Yu, Jifan Zhao, Shu Li, Juanzi Tang, Jie |
| contents | We introduce TableLLM, a robust large language model (LLM) with 8 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 evaluate the performance of TableLLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Our codes and data are publicly available at https://github.com/TableLLM/TableLLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19318 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios Zhang, Xiaokang Luo, Sijia Zhang, Bohan Ma, Zeyao Zhang, Jing Li, Yang Li, Guanlin Yao, Zijun Xu, Kangli Zhou, Jinchang Zhang-Li, Daniel Yu, Jifan Zhao, Shu Li, Juanzi Tang, Jie Computation and Language We introduce TableLLM, a robust large language model (LLM) with 8 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 evaluate the performance of TableLLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Our codes and data are publicly available at https://github.com/TableLLM/TableLLM. |
| title | TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.19318 |