{"ID":2832873,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.04550","arxiv_id":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","abstract":"The quadratic complexity of self-attention constrains Large Language Models (LLMs) in processing long contexts, a capability essential for many advanced applications. Context compression aims to alleviate this computational bottleneck while retaining critical semantic information. However, existing approaches often fall short: explicit methods may compromise local detail, whereas implicit methods can suffer from positional biases, information degradation, or an inability to capture long-range semantic dependencies. We propose AdmTree, a novel framework for adaptive, hierarchical context compression with a central focus on preserving high semantic fidelity while maintaining efficiency. AdmTree dynamically segments input based on information density, utilizing gist tokens to summarize variable-length segments as the leaves of a semantic binary tree. This structure, together with a lightweight aggregation mechanism and a frozen backbone LLM (thereby minimizing new trainable parameters), enables efficient hierarchical abstraction of the context. By preserving fine-grained details alongside global semantic coherence, mitigating positional bias, and dynamically adapting to content, AdmTree robustly retains the semantic information of long contexts.","short_abstract":"The quadratic complexity of self-attention constrains Large Language Models (LLMs) in processing long contexts, a capability essential for many advanced applications. Context compression aims to alleviate this computational bottleneck while retaining critical semantic information. However, existing approaches often fal...","url_abs":"https://arxiv.org/abs/2512.04550","url_pdf":"https://arxiv.org/pdf/2512.04550v1","authors":"[\"Yangning Li\",\"Shaoshen Chen\",\"Yinghui Li\",\"Yankai Chen\",\"Hai-Tao Zheng\",\"Hui Wang\",\"Wenhao Jiang\",\"Philip S. Yu\"]","published":"2025-12-04T08:04:19Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}