GenIC: An LLM-Based Framework for Instance Completion in Knowledge Graphs

• URL: http://arxiv.org/abs/2505.24036v1
• Date: Thu, 29 May 2025 22:15:25 GMT
• Title: GenIC: An LLM-Based Framework for Instance Completion in Knowledge Graphs
• Authors: Amel Gader, Alsayed Algergawy,
• Abstract summary: We introduce GenIC: a two-step Generative Instance Completion framework.<n>The first step focuses on property prediction, treated as a multi-label classification task.<n>The second step is link prediction, framed as a generative sequence-to-sequence task.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge graph completion aims to address the gaps of knowledge bases by adding new triples that represent facts. The complexity of this task depends on how many parts of a triple are already known. Instance completion involves predicting the relation-tail pair when only the head is given (h, ?, ?). Notably, modern knowledge bases often contain entity descriptions and types, which can provide valuable context for inferring missing facts. By leveraging these textual descriptions and the ability of large language models to extract facts from them and recognize patterns within the knowledge graph schema, we propose an LLM-powered, end-to-end instance completion approach. Specifically, we introduce GenIC: a two-step Generative Instance Completion framework. The first step focuses on property prediction, treated as a multi-label classification task. The second step is link prediction, framed as a generative sequence-to-sequence task. Experimental results on three datasets show that our method outperforms existing baselines. Our code is available at https://github.com/amal-gader/genic.

Related papers

• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [75.9865035064794]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• TransNet: Transfer Knowledge for Few-shot Knowledge Graph Completion [69.6049217133483]
  We propose a transfer learning-based few-shot KG completion method (TransNet)<n>By learning the relationships between different tasks, TransNet effectively transfers knowledge from similar tasks to improve the current task's performance.
  arXiv  Detail & Related papers  (2025-03-29T23:39:11Z)
• KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models [55.39134076436266]
  KG-CF is a framework tailored for ranking-based knowledge graph completion tasks.<n> KG-CF leverages LLMs' reasoning abilities to filter out irrelevant contexts, achieving superior results on real-world datasets.
  arXiv  Detail & Related papers  (2025-01-06T01:52:15Z)
• Is Large Language Model Good at Triple Set Prediction? An Empirical Study [12.094218772036596]
  The framework consists of LLM-based rule mining and LLM-based triple set prediction.<n>The experimental results indicate that when LLMs are required to adhere to a large amount of factual knowledge to predict missing triples, significant hallucinations occurs, leading to a noticeable decline in performance.
  arXiv  Detail & Related papers  (2024-12-24T14:03:07Z)
• Exploring Large Language Models for Knowledge Graph Completion [15.68895534638716]
  We consider triples in knowledge graphs as text sequences and introduce an innovative framework called Knowledge Graph LLM.<n>Our technique employs entity and relation descriptions of a triple as prompts and utilizes the response for predictions.<n> Experiments on various benchmark knowledge graphs demonstrate that our method attains state-of-the-art performance in tasks such as triple classification and relation prediction.
  arXiv  Detail & Related papers  (2023-08-26T16:51:17Z)
• Joint Language Semantic and Structure Embedding for Knowledge Graph Completion [66.15933600765835]
  We propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information. Our method embeds knowledge graphs for the completion task via fine-tuning pre-trained language models. Our experiments on a variety of knowledge graph benchmarks have demonstrated the state-of-the-art performance of our method.
  arXiv  Detail & Related papers  (2022-09-19T02:41:02Z)
• Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion [24.57087752710105]
  Few-shot KG completion aims to make predictions for triplets involving novel relations when only a few training triplets are provided as reference.<n>We propose a hierarchical relational learning method (HiRe) for few-shot KG completion.
  arXiv  Detail & Related papers  (2022-09-02T17:57:03Z)
• From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer [41.69537736842654]
  We provide an approach GenKGC, which converts knowledge graph completion to sequence-to-sequence generation task with the pre-trained language model. We introduce relation-guided demonstration and entity-aware hierarchical decoding for better representation learning and fast inference. We also release a new large-scale Chinese knowledge graph dataset AliopenKG500 for research purpose.
  arXiv  Detail & Related papers  (2022-02-04T12:52:32Z)
• KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation [100.79870384880333]
  We propose a knowledge-grounded pre-training (KGPT) to generate knowledge-enriched text. We adopt three settings, namely fully-supervised, zero-shot, few-shot to evaluate its effectiveness. Under zero-shot setting, our model achieves over 30 ROUGE-L on WebNLG while all other baselines fail.
  arXiv  Detail & Related papers  (2020-10-05T19:59:05Z)
• Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning [73.0598186896953]
  We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme. In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training.
  arXiv  Detail & Related papers  (2020-04-29T14:22:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.