# LINK-KG: LLM-Driven Coreference-Resolved Knowledge Graphs for Human Smuggling Networks

arXiv: https://arxiv.org/abs/2510.26486 · HTML: https://mlsanity.com/paper/2510.26486/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition](https://mlsanity.com/paper/2308.03279/) (2023)
- [Get my drift? Catching LLM Task Drift with Activation Deltas](https://mlsanity.com/paper/2406.00799/) (2024)
- [From human experts to machines: An LLM supported approach to ontology and knowledge graph construction](https://mlsanity.com/paper/2403.08345/) (2024)
- [Generalization Bias in Large Language Model Summarization of Scientific Research](https://mlsanity.com/paper/2504.00025/) (2025)
- [Exploring In-Context Learning Capabilities of Foundation Models for Generating Knowledge Graphs from Text](https://mlsanity.com/paper/2305.08804/) (2023)
- [An Open-Source Knowledge Graph Ecosystem for the Life Sciences](https://mlsanity.com/paper/2307.05727/) (2023)
- [Duplication Detection in Knowledge Graphs: Literature and Tools](https://mlsanity.com/paper/2004.08257/) (2020)
- [Coreference Resolution for Vietnamese Narrative Texts](https://mlsanity.com/paper/2504.19606/) (2025)

## Built on by (most cited first, 2 of 2)

- [SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction](https://mlsanity.com/paper/2601.10003/) (2026)
- [FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs](https://mlsanity.com/paper/2606.19710/) (2026)

## Abstract (arXiv)

Human smuggling networks are complex and constantly evolving, making them difficult to analyze comprehensively. Legal case documents offer rich factual and procedural insights into these networks but are often long, unstructured, and filled with ambiguous or shifting references, posing significant challenges for automated knowledge graph (KG) construction. Existing methods either overlook coreference resolution or fail to scale beyond short text spans, leading to fragmented graphs and inconsistent entity linking. We propose LINK-KG, a modular framework that integrates a three-stage, LLM-guided coreference resolution pipeline with downstream KG extraction. At the core of our approach is a type-specific Prompt Cache, which consistently tracks and resolves references across document chunks, enabling clean and disambiguated narratives for structured knowledge graph construction from both short and long legal texts. LINK-KG reduces average node duplication by 45.21% and noisy nodes by 32.22% compared to baseline methods, resulting in cleaner and more coherent graph structures. These improvements establish LINK-KG as a strong foundation for analyzing complex criminal networks.