---
title: "野数据分析：大语言模型在真实世界数据复杂性下的基准测试"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.06482v1"
permalink: "https://feed.astralor.com/items/itm_c140d494710cb60e0daabd99"
published: "2026-07-07T16:43:05.000Z"
score: 79
channel: "ai"
tags: ["DataGovBench","大语言模型","政府开放数据","数据分析","数据基准测试","智能体框架"]
---

# 野数据分析：大语言模型在真实世界数据复杂性下的基准测试

## AI 点评

> 这篇论文最值得关注的地方在于它戳破了当前LLM在数据分析能力上的“泡沫”——许多模型在简单基准上表现优异，但一碰到多表、需要推理和创造性的真实数据就捉襟见肘。对于AI产品经理、数据科学家和模型开发者来说，DataGovBench是一个极具参考价值的测试床。谁先在这个基准上取得突破，谁就能在下一代智能数据分析工具中占据先机。

## 速览

现有评估大语言模型数据分析能力的基准往往脱离真实场景，仅关注小表格的事实检索，忽略了多表数据、外部知识整合和探索性洞察发现。该研究推出了 DataGovBench，一个基于政府开放数据的基准，包含表问答和表洞察两项任务。实验表明，当前最先进的LLM（包括使用智能体框架）在这两项任务上存在显著性能差距，远未达到真实数据分析的需求。代码和数据已公开。

## 关键点

- 现有数据分析基准过于简化，无法反映真实世界的多表、需外部知识和探索性分析等复杂场景。
- 推出了 DataGovBench，包含表问答（复杂可分解问题+文本/可视化答案）和表洞察（生成专家级发现）两项任务。
- 全面实验表明，当前最先进的LLM（包括使用智能体框架）在两项任务上均存在显著性能差距。
- 揭示了LLM在真实数据分析场景中的严重不足，为未来研究提供了挑战性基准。

## 全文

Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fact retrieval from small tables and overlook the challenges of large multi-tabular datasets, external knowledge integration, and exploratory insight discovery. We introduce DataGovBench, a benchmark derived from governmental open data designed to evaluate LLMs in practical scenarios. The benchmark includes two tasks: Table QA that requires solving complex decomposable questions and producing textual answers or visualizations, and Table Insight that evaluates the ability of models to generate expert-level findings through exploratory data analysis. Comprehensive experiments with state-of-the-art LLMs, both with and without agentic frameworks, reveal significant performance gaps across both tasks. These results suggest that current LLM-based systems remain far from satisfying the demands of real-world data analytics. DataGovBench provides a challenging benchmark for advancing research on LLMs capable of both answering analytical queries and discovering insights from data. Code and sample data are available at https://github.com/SoHasegawa/datagovbench.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_c140d494710cb60e0daabd99