Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate

TL;DR

AgentEA is a multi-agent debate framework that improves entity alignment across knowledge graphs by enhancing embedding quality and employing a two-stage debate process for more reliable decisions.

Contribution

It introduces a two-stage multi-role debate mechanism combined with entity representation optimization to improve the reliability of entity alignment.

Findings

Effective in cross-lingual, sparse, large-scale, and heterogeneous settings.

Outperforms existing methods on public benchmarks.

Enhances alignment decision reliability through multi-agent debate.

Abstract

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.