← Back to all news
arXiv Machine Learning By Yuanning Cui, Zequn Sun, Wei Hu, Kexuan Xin, Zhangjie Fu

Breaking the Reasoning Horizon in Entity Alignment Foundation Models

Read the original on arXiv Machine Learning →

The paper introduces a new entity alignment foundation model that overcomes the limitations of existing models by addressing the "reasoning horizon gap". It employs a parallel encoding strategy that uses seed entity pairs as local anchors to guide message passing, thereby shortening inference paths and improving alignment across sparse, heterogeneous knowledge graphs. The model also incorporates a merged relation graph and a learnable interaction module, and experimental results demonstrate its strong generalizability to unseen knowledge graphs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Oct 5

Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching

Enrich-on-Graph (EoG) is a flexible framework that uses large language models to enrich knowledge graphs, thereby bridging the semantic gap between structured graphs and unstructured queries in complex reasoning tasks. By leveraging LLMs’ prior knowledge, EoG enables efficient evidence extraction from knowledge graphs, achieving precise and robust reasoning while maintaining low computational costs and scalability. The authors also introduce three graph quality evaluation metrics for query‑graph alignment, theoretically validate their optimization objectives, and demonstrate state‑of‑the‑art performance on two KGQA benchmark datasets.

By Songze Li, Zhiqiang Liu, Zhengke Gui, Huajun Chen, Wen Zhang
llmsnlpbenchmarkssafety
More like this →
arXiv Computation and Language
2d ago

Every Little Helps: Building Knowledge Graph Foundation Model with Fine-grained Transferable Multi-modal Tokens

The paper introduces TOFU, a token-based foundation model for multi‑modal knowledge graph reasoning (MMKGR). TOFU converts structural, visual, and textual data into modality‑specific tokens and uses a hierarchical fusion architecture with mixture‑of‑message mechanisms to learn transferable features. Experiments on 17 MMKGs demonstrate that TOFU outperforms existing KGFM and MMKGR baselines, especially on unseen knowledge graphs.

By Yichi Zhang, Zhuo Chen, Lingbing Guo, Wen Zhang, Huajun Chen
ragmultimodal
More like this →