arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.11986cs.AI
收藏

大型语言模型在概念数据库建模中的局限性

On the Limitations of Large Language Models for Conceptual Database Modeling

Systems and Computing Department(系统与计算系)

Arthur F. Siqueira, Carlos D. S. Nogueira, Eduarda Farias, Claudio E. C. Campelo, Júlia Menezes

AI总结:

本文研究了大型语言模型在生成实体关系图方面的能力,发现其在复杂场景中可靠性下降,存在不一致和模糊性问题。

摘要:

本文分析了大型语言模型(LLMs)在关系数据库概念建模中的应用,通过自然语言需求自动生成实体-关系(ER)图。该方法结合不同语言模型与提示工程技术,评估其在识别实体、关系和属性方面的一致性。实验评估涉及三个LLM,分别应用零样本、链式思维和链式思维+验证器提示技术,应用于相同需求场景,逐步增加复杂性。生成的图表通过直接比较文本需求进行定性分析,考虑结构和语义的符合程度。结果表明,尽管LLM在简单场景中表现合理,但随着需求复杂性增加,不一致、模糊性和约束表示失败的问题增加。这些发现表明,目前LLM在复杂场景中尚不成熟,验证成本可能抵消显而易见的生产效率提升。

英文摘要:

This article analyzes the use of Large Language Models (LLMs) as support for the conceptual modeling of relational databases through the automatic generation of Entity-Relationship (ER) diagrams from natural language requirements. The approach combines different language models with prompt engineering techniques to evaluate their ability to identify entities, relationships, and attributes in a conceptually consistent manner. The experimental evaluation involved three LLMs, each subjected to three prompting techniques (Zero-Shot, Chain of Thought, and Chain of Thought + Verifier), applied to the same requirements scenario with progressively increasing complexity. The generated diagrams were qualitatively analyzed through direct comparison with the textual requirements, considering the structural and semantic adherence of the modeled elements. The results indicate that, although LLMs show reasonable performance in less complex scenarios, their reliability decreases as the complexity of the requirements increases, with a rise in inconsistencies, ambiguities, and failures in representing constraints. These findings reinforce that, in their current state, LLMs are not sufficiently mature for reliable use in complex scenarios, and the cost of validation may offset the apparent productivity gains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑