Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918208467894272 |
|---|---|
| author | Li, Yu Huang, Yi Qi, Guilin Feng, Junlan Hu, Nan Zhai, Songlin Xue, Haohan Chen, Yongrui Shen, Ruoyan Wu, Tongtong |
| author_facet | Li, Yu Huang, Yi Qi, Guilin Feng, Junlan Hu, Nan Zhai, Songlin Xue, Haohan Chen, Yongrui Shen, Ruoyan Wu, Tongtong |
| contents | Knowledge graphs are widely used in industrial applications, making error detection crucial for ensuring the reliability of downstream applications. Existing error detection methods often fail to effectively utilize fine-grained subgraph information and rely solely on fixed graph structures, while also lacking transparency in their decision-making processes, which results in suboptimal detection performance. In this paper, we propose a novel Multi-Agent framework for Knowledge Graph Error Detection (MAKGED) that utilizes multiple large language models (LLMs) in a collaborative setting. By concatenating fine-grained, bidirectional subgraph embeddings with LLM-based query embeddings during training, our framework integrates these representations to produce four specialized agents. These agents utilize subgraph information from different dimensions to engage in multi-round discussions, thereby improving error detection accuracy and ensuring a transparent decision-making process. Extensive experiments on FB15K and WN18RR demonstrate that MAKGED outperforms state-of-the-art methods, enhancing the accuracy and robustness of KG evaluation. For specific industrial scenarios, our framework can facilitate the training of specialized agents using domain-specific knowledge graphs for error detection, which highlights the potential industrial application value of our framework. Our code and datasets are available at https://github.com/kse-ElEvEn/MAKGED. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15791 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs Li, Yu Huang, Yi Qi, Guilin Feng, Junlan Hu, Nan Zhai, Songlin Xue, Haohan Chen, Yongrui Shen, Ruoyan Wu, Tongtong Artificial Intelligence Multiagent Systems Knowledge graphs are widely used in industrial applications, making error detection crucial for ensuring the reliability of downstream applications. Existing error detection methods often fail to effectively utilize fine-grained subgraph information and rely solely on fixed graph structures, while also lacking transparency in their decision-making processes, which results in suboptimal detection performance. In this paper, we propose a novel Multi-Agent framework for Knowledge Graph Error Detection (MAKGED) that utilizes multiple large language models (LLMs) in a collaborative setting. By concatenating fine-grained, bidirectional subgraph embeddings with LLM-based query embeddings during training, our framework integrates these representations to produce four specialized agents. These agents utilize subgraph information from different dimensions to engage in multi-round discussions, thereby improving error detection accuracy and ensuring a transparent decision-making process. Extensive experiments on FB15K and WN18RR demonstrate that MAKGED outperforms state-of-the-art methods, enhancing the accuracy and robustness of KG evaluation. For specific industrial scenarios, our framework can facilitate the training of specialized agents using domain-specific knowledge graphs for error detection, which highlights the potential industrial application value of our framework. Our code and datasets are available at https://github.com/kse-ElEvEn/MAKGED. |
| title | Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2501.15791 |