AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918231258693632 |
|---|---|
| author | Li, Yangning Chen, Shaoshen Li, Yinghui Chen, Yankai Zheng, Hai-Tao Wang, Hui Jiang, Wenhao Yu, Philip S. |
| author_facet | Li, Yangning Chen, Shaoshen Li, Yinghui Chen, Yankai Zheng, Hai-Tao Wang, Hui Jiang, Wenhao Yu, Philip S. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04550 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees Li, Yangning Chen, Shaoshen Li, Yinghui Chen, Yankai Zheng, Hai-Tao Wang, Hui Jiang, Wenhao Yu, Philip S. Computation and Language Artificial Intelligence 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. |
| title | AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.04550 |