# GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models

arXiv: https://arxiv.org/abs/2408.10819 · HTML: https://mlsanity.com/paper/2408.10819/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://mlsanity.com/paper/2010.15980/) (2020)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models](https://mlsanity.com/paper/2203.02167/) (2022)
- [GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models](https://mlsanity.com/paper/2310.07793/) (2023)
- [Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models](https://mlsanity.com/paper/2403.01972/) (2024)
- [Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancement](https://mlsanity.com/paper/2310.08279/) (2023)
- [Start from Zero: Triple Set Prediction for Automatic Knowledge Graph Completion](https://mlsanity.com/paper/2406.18166/) (2024)

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

- [Toward Real-World IoT Security: Concept Drift-Resilient IoT Botnet Detection via Latent Space Representation Learning and Alignment](https://mlsanity.com/paper/2512.22488/) (2025)
- [TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation](https://mlsanity.com/paper/2606.00029/) (2026)

## Abstract (arXiv)

Knowledge graph completion (KGC) focuses on identifying missing triples in a knowledge graph (KG) , which is crucial for many downstream applications. Given the rapid development of large language models (LLMs), some LLM-based methods are proposed for KGC task. However, most of them focus on prompt engineering while overlooking the fact that finer-grained subgraph information can aid LLMs in generating more accurate answers. In this paper, we propose a novel completion framework called Generative Subgraph-based KGC (GS-KGC), which utilizes subgraph information as contextual reasoning and employs a QA approach to achieve the KGC task. This framework primarily includes a subgraph partitioning algorithm designed to generate negatives and neighbors. Specifically, negatives can encourage LLMs to generate a broader range of answers, while neighbors provide additional contextual insights for LLM reasoning. Furthermore, we found that GS-KGC can discover potential triples within the KGs and new facts beyond the KGs. Experiments conducted on four common KGC datasets highlight the advantages of the proposed GS-KGC, e.g., it shows a 5.6% increase in Hits@3 compared to the LLM-based model CP-KGC on the FB15k-237N, and a 9.3% increase over the LLM-based model TECHS on the ICEWS14.