大模型
arxiv.org ·
论大型语言模型在概念数据库建模中的局限性
该 arXiv 论文（v2）研究用 LLM 从自然语言需求自动生成实体-关系（ER）图，以支持关系数据库概念建模。实验选取 3 个语言模型，分别采用 Zero-Shot、Chain of Thought、Chain of Thought + Verifier 三种提示技术，在复杂度逐步提升的同一需求场景下生成图，并与文本需求做结构与语义一致性比对。结果显示，LLM 在低复杂度场景表现尚可，但随着需求复杂度上升，不一致、歧义和约束表达失败增多；作者认为当前 LLM 尚不足以在复杂场景可靠使用，验证成本可能抵消其带来的生产力收益。
AI推荐理由 arXiv 论文（v2，2026-09-18 修订），实验设计明确：3 个 LLM × 3 种提示技术（Zero-Shot、CoT、CoT+Verifier），在复杂度递增的需求场景下生成 ER 图并与文本需求做定性比对。具体新信息是随需求复杂度上升，实体/关系/属性识别的不一致、歧义与约束表达失败增多，作者据此认为当前 LLM 在复杂场景尚不可靠、验证成本可能抵消表面生产力收益。局限：摘要未给出模型名称、样本量与量化指标，结论为定性判断，不能外推为所有建模任务。
72
正文
Computer Science > Artificial Intelligence
arXiv:2605.11986 (cs)
[Submitted on 12 May 2026 (v1), last revised 18 Sep 2026 (this version, v2)]
Title:On the Limitations of Large Language Models for Conceptual Database Modeling
Authors:Arthur F. Siqueira, Carlos D. S. Nogueira, Eduarda Farias, Claudio E. C. Campelo, Júlia Menezes
View a PDF of the paper titled On the Limitations of Large Language Models for Conceptual Database Modeling, by Arthur F. Siqueira and 3 other authors
View PDF
HTML (experimental)
Abstract: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.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2605.11986 [cs.AI]
(or
arXiv:2605.11986v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.11986
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Arthur Félix De Siqueira [view email]
[v1]
Tue, 12 May 2026 11:35:59 UTC (193 KB)
[v2]
Fri, 18 Sep 2026 17:59:25 UTC (533 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled On the Limitations of Large Language Models for Conceptual Database Modeling, by Arthur F. Siqueira and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)