@inproceedings{ding-etal-2026-gase,
    title = "{GASE}: Graph-Aware Semantic Embedding Learning with Frozen {LLM}s for Text-Attributed Graphs",
    author = "Ding, Mingqian  and
      Li, Jianjun  and
      Yang, Wenqi  and
      Zhang, Zhibo  and
      Fang, Yushen",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1434/",
    pages = "31073--31086",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Models (LLMs) have shown strong potential for text-attributed graph (TAG) learning, yet effectively integrating LLM semantics with graph structural information remains challenging. Embeddings obtained from frozen LLMs lack topology awareness, while fine-tuning LLMs is often computationally expensive. Moreover, LLM embeddings are high-dimensional, and naively reducing dimensionality tends to destroy semantics. To address these issues, we propose GASE, a framework for learning Graph-Aware Semantic Embeddings using frozen LLMs. GASE consists of two key stages: First, we introduce a Training-Free Structure-Aware Semantic Extraction (TSSE) module. Through inter-layer semantic feedback and progressive masked attention, it efficiently compresses and propagates semantic context from neighboring nodes without updating LLM parameters. Second, we propose a Subspace Decomposition and Structural Injection (SDSI) strategy. Embeddings obtained from TSSE are decomposed into a semantic-rich subspace and a structural injection subspace, and structural signals are injected into the latter, which preserves original semantics while integrating graph information. Experiments demonstrate that GASE outperforms state-of-the-art baselines on node classification and achieves a 5{\texttimes} speedup over fine-tuning-based methods."
}