# Automated Construction of Theme-specific Knowledge Graphs

arXiv: https://arxiv.org/abs/2404.19146 · HTML: https://mlsanity.com/paper/2404.19146/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 58 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [Automated Phrase Mining from Massive Text Corpora](https://mlsanity.com/paper/1702.04457/) (2017)
- [GPT-RE: In-context Learning for Relation Extraction using Large Language Models](https://mlsanity.com/paper/2305.02105/) (2023)
- [IMoJIE: Iterative Memory-Based Joint Open Information Extraction](https://mlsanity.com/paper/2005.08178/) (2020)
- [Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs](https://mlsanity.com/paper/2305.09858/) (2023)
- [MolTC: Towards Molecular Relational Modeling In Language Models](https://mlsanity.com/paper/2402.03781/) (2024)
- [Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning](https://mlsanity.com/paper/2205.02355/) (2022)
- [Few-Shot Document-Level Relation Extraction](https://mlsanity.com/paper/2205.02048/) (2022)
- [Open-Vocabulary Argument Role Prediction for Event Extraction](https://mlsanity.com/paper/2211.01577/) (2022)
- [DocOIE: A Document-level Context-Aware Dataset for OpenIE](https://mlsanity.com/paper/2105.04271/) (2021)
- [Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning](https://mlsanity.com/paper/1711.03226/) (2017)
- [Graphene: Semantically-Linked Propositions in Open Information Extraction](https://mlsanity.com/paper/1807.11276/) (2018)
- [MedML: Fusing Medical Knowledge and Machine Learning Models for Early Pediatric COVID-19 Hospitalization and Severity Prediction](https://mlsanity.com/paper/2207.12283/) (2022)
- [Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models](https://mlsanity.com/paper/2305.15597/) (2023)
- [Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction](https://mlsanity.com/paper/2312.03022/) (2023)
- [Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction](https://mlsanity.com/paper/2401.11800/) (2024)
- [Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation](https://mlsanity.com/paper/2312.05276/) (2023)
- [Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction](https://mlsanity.com/paper/2312.12021/) (2023)
- [Comparison of pipeline, sequence-to-sequence, and GPT models for end-to-end relation extraction: experiments with the rare disease use-case](https://mlsanity.com/paper/2311.13729/) (2023)

## Built on by (most cited first, 16 of 16)

- [Combining Knowledge Graphs and Large Language Models](https://mlsanity.com/paper/2407.06564/) (2024)
- [iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models](https://mlsanity.com/paper/2409.03284/) (2024)
- [An Automatic Graph Construction Framework based on Large Language Models for Recommendation](https://mlsanity.com/paper/2412.18241/) (2024)
- [A Survey on Retrieval And Structuring Augmented Generation with Large Language Models](https://mlsanity.com/paper/2509.10697/) (2025)
- [Scaling Knowledge Graph Construction through Synthetic Data Generation and Distillation](https://mlsanity.com/paper/2410.16597/) (2024)
- [Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey](https://mlsanity.com/paper/2505.03418/) (2025)
- [MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph](https://mlsanity.com/paper/2508.12393/) (2025)
- [LKD-KGC: Domain-Specific KG Construction via LLM-driven Knowledge Dependency Parsing](https://mlsanity.com/paper/2505.24163/) (2025)
- [FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graph](https://mlsanity.com/paper/2508.00961/) (2025)
- [Structure-Augmented Reasoning Generation](https://mlsanity.com/paper/2506.08364/) (2025)
- [Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction](https://mlsanity.com/paper/2509.03540/) (2025)
- [Hierarchical Knowledge Graph Construction from Images for Scalable E-Commerce](https://mlsanity.com/paper/2410.21237/) (2024)
- [Automated Domain Question Mapping (DQM) with Educational Learning Materials](https://mlsanity.com/paper/2601.07062/) (2026)
- [Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems](https://mlsanity.com/paper/2605.19366/) (2026)
- [Slides2MindMap: Reconstructing Cognitively Efficient Knowledge Hierarchies from Lecture Slides](https://mlsanity.com/paper/2608.00610/) (2026)
- [EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models](https://mlsanity.com/paper/2609.00479/) (2026)

## Abstract (arXiv)

Despite widespread applications of knowledge graphs (KGs) in various tasks such as question answering and intelligent conversational systems, existing KGs face two major challenges: information granularity and deficiency in timeliness. These hinder considerably the retrieval and analysis of in-context, fine-grained, and up-to-date knowledge from KGs, particularly in highly specialized themes (e.g., specialized scientific research) and rapidly evolving contexts (e.g., breaking news or disaster tracking). To tackle such challenges, we propose a theme-specific knowledge graph (i.e., ThemeKG), a KG constructed from a theme-specific corpus, and design an unsupervised framework for ThemeKG construction (named TKGCon). The framework takes raw theme-specific corpus and generates a high-quality KG that includes salient entities and relations under the theme. Specifically, we start with an entity ontology of the theme from Wikipedia, based on which we then generate candidate relations by Large Language Models (LLMs) to construct a relation ontology. To parse the documents from the theme corpus, we first map the extracted entity pairs to the ontology and retrieve the candidate relations. Finally, we incorporate the context and ontology to consolidate the relations for entity pairs. We observe that directly prompting GPT-4 for theme-specific KG leads to inaccurate entities (such as "two main types" as one entity in the query result) and unclear (such as "is", "has") or wrong relations (such as "have due to", "to start"). In contrast, by constructing the theme-specific KG step by step, our model outperforms GPT-4 and could consistently identify accurate entities and relations. Experimental results also show that our framework excels in evaluations compared with various KG construction baselines.