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

arXiv: https://arxiv.org/abs/2604.13551 · HTML: https://mlsanity.com/paper/2604.13551/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 76 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)
- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 22 of 22)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment](https://mlsanity.com/paper/1611.03954/) (2016)
- [A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs](https://mlsanity.com/paper/2003.07743/) (2020)
- [Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/1908.08210/) (2019)
- [Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation](https://mlsanity.com/paper/1911.08936/) (2019)
- [Multi-Channel Graph Neural Network for Entity Alignment](https://mlsanity.com/paper/1908.09898/) (2019)
- [Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs](https://mlsanity.com/paper/1905.04914/) (2019)
- [TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs](https://mlsanity.com/paper/2004.13579/) (2020)
- [Jointly Learning Entity and Relation Representations for Entity Alignment](https://mlsanity.com/paper/1909.09317/) (2019)
- [Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining](https://mlsanity.com/paper/2103.15452/) (2021)
- [SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs](https://mlsanity.com/paper/2203.01044/) (2022)
- [Collective Entity Alignment via Adaptive Features](https://mlsanity.com/paper/1912.08404/) (2019)
- [Removal of Hallucination on Hallucination: Debate-Augmented RAG](https://mlsanity.com/paper/2505.18581/) (2025)
- [Multi-Agent Large Language Models for Conversational Task-Solving](https://mlsanity.com/paper/2410.22932/) (2024)
- [Unlocking the Power of Large Language Models for Entity Alignment](https://mlsanity.com/paper/2402.15048/) (2024)
- [Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets](https://mlsanity.com/paper/2304.03468/) (2023)
- [Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment](https://mlsanity.com/paper/2401.16960/) (2024)
- [OntoTKGE: Ontology-Enhanced Temporal Knowledge Graph Extrapolation](https://mlsanity.com/paper/2604.05468/) (2026)

## Abstract (arXiv)

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.