JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chi, Ce, Wang, Xing, Wang, Zhendong, Liu, Xiaofan, Li, Ce, Song, Zhiyan, Zhao, Chen, Yang, Kexin, Shi, Boshen, Yang, Jingjing, Deng, Chao, Feng, Junlan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909947922481152
author Chi, Ce
Wang, Xing
Wang, Zhendong
Liu, Xiaofan
Li, Ce
Song, Zhiyan
Zhao, Chen
Yang, Kexin
Shi, Boshen
Yang, Jingjing
Deng, Chao
Feng, Junlan
author_facet Chi, Ce
Wang, Xing
Wang, Zhendong
Liu, Xiaofan
Li, Ce
Song, Zhiyan
Zhao, Chen
Yang, Kexin
Shi, Boshen
Yang, Jingjing
Deng, Chao
Feng, Junlan
contents In this work, we present JT-DA-8B (JiuTian Data Analyst 8B), a specialized large language model designed for complex table reasoning tasks across diverse real-world scenarios. To address the lack of high-quality supervision in tabular reasoning scenarios, we construct a comprehensive and diverse training corpus with 34 well-defined table reasoning tasks, by aggregating 29 public table QA datasets and 3 million tables. An automatic pipeline is proposed to generate realistic multi-step analytical tasks involving reasoning patterns. The model is trained upon open-source JT-Coder-8B model, an 8B-parameter decoder-only foundation model trained from scratch. In the training stage, we leverage LLM-based scoring and workflow-aligned filtering to distill high-quality, table-centric data. Both supervised fine-tuning (SFT) and Reinforcement learning (RL) are adopted to optimize our model. Afterwards, a four-stage table reasoning workflow is proposed, including table preprocessing, table sensing, tool-integrated reasoning, and prompt engineering, to improve model interpretability and execution accuracy. Experimental results show that JT-DA-8B achieves strong performance in various table reasoning tasks, demonstrating the effectiveness of data-centric generation and workflow-driven optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06859
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models
Chi, Ce
Wang, Xing
Wang, Zhendong
Liu, Xiaofan
Li, Ce
Song, Zhiyan
Zhao, Chen
Yang, Kexin
Shi, Boshen
Yang, Jingjing
Deng, Chao
Feng, Junlan
Artificial Intelligence
In this work, we present JT-DA-8B (JiuTian Data Analyst 8B), a specialized large language model designed for complex table reasoning tasks across diverse real-world scenarios. To address the lack of high-quality supervision in tabular reasoning scenarios, we construct a comprehensive and diverse training corpus with 34 well-defined table reasoning tasks, by aggregating 29 public table QA datasets and 3 million tables. An automatic pipeline is proposed to generate realistic multi-step analytical tasks involving reasoning patterns. The model is trained upon open-source JT-Coder-8B model, an 8B-parameter decoder-only foundation model trained from scratch. In the training stage, we leverage LLM-based scoring and workflow-aligned filtering to distill high-quality, table-centric data. Both supervised fine-tuning (SFT) and Reinforcement learning (RL) are adopted to optimize our model. Afterwards, a four-stage table reasoning workflow is proposed, including table preprocessing, table sensing, tool-integrated reasoning, and prompt engineering, to improve model interpretability and execution accuracy. Experimental results show that JT-DA-8B achieves strong performance in various table reasoning tasks, demonstrating the effectiveness of data-centric generation and workflow-driven optimization.
title JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2512.06859