@inproceedings{yan-etal-2025-inductive,
    title = "Inductive Reasoning on Few-Shot Knowledge Graphs with Task-Aware Language Models",
    author = "Yan, Cheng  and
      Zhao, Feng  and
      Zhao, Ruilin  and
      Zhang, Hong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.677/",
    doi = "10.18653/v1/2025.findings-emnlp.677",
    pages = "12656--12666",
    ISBN = "979-8-89176-335-7",
    abstract = "Knowledge graphs are dynamic structures that continuously evolve as new entities emerge, often accompanied by only a handful of associated triples. Current knowledge graph reasoning methods struggle in these few-shot scenarios due to their reliance on extensive structural information.To address this limitation, we introduce ENGRAM, a novel approach that enables inductive reasoning on few-shot KGs by innovatively enriching the semantics from both textual and structural perspectives. Our key innovation lies in designing a task-aware language model that activates the language model{'}s in-context learning ability for structured KG tasks, effectively bridging the gap between unstructured natural language and structured tasks. Unlike prior methods that inefficiently employ classification over exhaustive candidate sets, we recast knowledge graph reasoning from a generative perspective, allowing for direct computation of inference results without iterative enumeration. Additionally, we propose a distant neighborhood awareness strategy to enrich the sparse structural features of few-shot entities.Our experimental findings indicate that our method not only achieves state-of-the-art performance in few-shot scenarios. The tunable parameters of our model are approximately 1{\%} of those in previous language model-based methods, and the inference time has been reduced to 1/10 of that required by previous methods."
}