Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate
For entity alignment tasks in knowledge graph integration, AgentEA addresses the reliability of candidate sets and LLM reasoning, offering a more robust solution than existing methods.
AgentEA improves entity alignment across knowledge graphs by using a two-stage multi-agent debate mechanism, achieving up to 10% higher Hit@1 than prior LLM-based methods on cross-lingual and sparse benchmarks.
Entity alignment (EA) aims to identify entities referring to the same real-world object across different knowledge graphs (KGs). Recent approaches based on large language models (LLMs) typically obtain entity embeddings through knowledge representation learning and use embedding similarity to identify an alignment-uncertain entity set. For each uncertain entity, a candidate entity set (CES) is then retrieved based on embedding similarity to support subsequent alignment reasoning and decision making. However, the reliability of the CES and the reasoning capability of LLMs critically affect the effectiveness of subsequent alignment decisions. To address this issue, we propose AgentEA, a reliable EA framework based on multi-agent debate. AgentEA first improves embedding quality through entity representation preference optimization, and then introduces a two-stage multi-role debate mechanism consisting of lightweight debate verification and deep debate alignment to progressively enhance the reliability of alignment decisions while enabling more efficient debate-based reasoning. Extensive experiments on public benchmarks under cross-lingual, sparse, large-scale, and heterogeneous settings demonstrate the effectiveness of AgentEA.