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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Cunda, Ma, Ziying, Hu, Po, Wang, Weihua, Bao, Feilong
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915938062827520
author Wang, Cunda
Ma, Ziying
Hu, Po
Wang, Weihua
Bao, Feilong
author_facet Wang, Cunda
Ma, Ziying
Hu, Po
Wang, Weihua
Bao, Feilong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13551
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate
Wang, Cunda
Ma, Ziying
Hu, Po
Wang, Weihua
Bao, Feilong
Computation and Language
Information Retrieval
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.
title Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2604.13551