# Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs

arXiv: https://arxiv.org/abs/2501.15791 · HTML: https://mlsanity.com/paper/2501.15791/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 27 Jan 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [Knowledge Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1904.12575/) (2019)
- [Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting](https://mlsanity.com/paper/2307.01709/) (2023)
- [Discriminative Predicate Path Mining for Fact Checking in Knowledge Graphs](https://mlsanity.com/paper/1510.05911/) (2015)
- [MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation](https://mlsanity.com/paper/2403.19305/) (2024)
- [Triple Trustworthiness Measurement for Knowledge Graph](https://mlsanity.com/paper/1809.09414/) (2018)
- [Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence](https://mlsanity.com/paper/1705.03202/) (2017)
- [Contrastive Knowledge Graph Error Detection](https://mlsanity.com/paper/2211.10030/) (2022)
- [KGClean: An Embedding Powered Knowledge Graph Cleaning Framework](https://mlsanity.com/paper/2004.14478/) (2020)
- [Knowledge Graph Error Detection with Contrastive Confidence Adaption](https://mlsanity.com/paper/2312.12108/) (2023)

## Built on by (most cited first, 5 of 5)

- [PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning](https://mlsanity.com/paper/2602.13691/) (2026)
- [C3TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation](https://mlsanity.com/paper/2511.09292/) (2025)
- [Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges](https://mlsanity.com/paper/2607.26212/) (2026)
- [Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification](https://mlsanity.com/paper/2604.04190/) (2026)
- [Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents](https://mlsanity.com/paper/2610.02330/) (2026)

## Abstract (arXiv)

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.