Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Entity alignment (EA) is a fundamental task in knowledge graph (KG) integration, aiming to identify equivalent entities across different KGs for a unified and comprehensive representation. Recent advances have explored pre-trained language models (PLMs) to enhance the semantic understanding of entities, achieving notable improvements. However, existing methods face two major limitations. First, they rely heavily on human-annotated labels for training, leading to high computational costs and poor scalability. Second, some approaches use large language models (LLMs) to predict alignments in a multi-choice question format, but LLM outputs may deviate from expected formats, and predefined options may exclude correct matches, leading to suboptimal performance. To address these issues, we propose LEA, an LLM-augmented entity alignment framework that eliminates the need for labeled data and enhances robustness by mitigating information heterogeneity at both embedding and semantic levels. LEA first introduces an entity textualization module that transforms structural and textual information into a unified format, ensuring consistency and improving entity representations. It then leverages LLMs to enrich entity descriptions, enhancing semantic distinctiveness. Finally, these enriched descriptions are encoded into a shared embedding space, enabling efficient alignment through text retrieval techniques. To balance performance and computational cost, we further propose a selective augmentation strategy that prioritizes the most ambiguous entities for refinement. Experimental results on both homogeneous and heterogeneous KGs demonstrate that LEA outperforms existing models trained on 30 % labeled data, achieving a 30 % absolute improvement in Hit@1 score. As LLMs and text embedding models advance, LEA is expected to further enhance EA performance, providing a scalable and robust paradigm for practical applications. The code and dataset can be found at https://github.com/Longmeix/LEA.

Pedestrian trajectory prediction aims to forecast future trajectories based on observed behaviors and surrounding conditions, and it is critical for applications like autonomous driving. Predicting trajectories in unseen scenes is challenging due to varying environments, elusive internal movement patterns, and complex social interactions. Existing methods face two limitations. Firstly, they struggle to effectively extract internal movement patterns from historical trajectories without labeled samples, which are often inaccessible in practice. Secondly, they fail to learn social interaction patterns across scenes, particularly when using angle-related features that are noise-sensitive and not strictly invariant to Euclidean transformations. To address these challenges, this paper introduces a Geometry-guided Behavior Pattern Adaptation (GBPA) method based on two geometric observations. Firstly, properly normalized historical trajectories are distributionally similar to full trajectories, allowing generation of pseudo-full trajectories for auxiliary training. Secondly, the discretized angular partitions, created by splitting the perceptive field into equal-sized fans, are invariant to Euclidean transformations and robust to noise. GBPA employs a test-time training strategy on scaled historical trajectories (T3SH) to adapt internal movement patterns without future trajectories and an angular partitioned attention (APA) mechanism to capture transferable social interaction patterns by differentiating neighbors’ effects. Experimental results on two datasets demonstrate that GBPA significantly improves prediction performance.