@inproceedings{zhang-etal-2026-beyond-task,
    title = "Beyond Task-Level Context: Class-Conditional Context Vectors for Implicit In-Context Learning",
    author = "Zhang, Jianxin  and
      Hu, Yilu  and
      Liu, Teng  and
      Guo, Pei  and
      Li, Juntao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1527/",
    pages = "30543--30566",
    ISBN = "979-8-89176-395-1",
    abstract = "Implicit In-Context Learning compresses demonstration examples into a single context vector and injects it into the model{'}s activation space, achieving few-shot-level performance at near zero-shot inference cost. However, existing approaches typically aggregate demonstrations from all classes into a shared, task-level context vector, capturing global task information but without explicitly preserving fine-grained, class-conditional semantic distinctions. In this work, we propose Class-Conditional Context Vectors (C{3}V), a simple yet effective extension to implicit in-context learning that explicitly models class-specific contextual information by constructing separate context vectors for each class, without relying on explicit prompts. These class-conditional context vectors are additively injected into the model{'}s residual streams in a single forward pass, enabling contextual contributions to be modulated in a class-aware manner while keeping the backbone frozen. We evaluate C{3}V on multiple text classification benchmarks across several families of large language models. Experimental results demonstrate that C{3}V consistently outperforms task-level context vector baselines, and achieves higher average accuracy than conventional few-shot learning on most models."
}