用大模型解压压缩文本，只保留任务关键语义。
SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors
- 将文本压缩为可由大模型解码的语义代码，不追求完全还原。
- 结构化散文恢复效果最好，语义原子召回率0.956，节省19.1%令牌。
- 适合需要轻量化传输但保留核心语义的场景，如智能客服、摘要系统。
大型语言模型（LLM）系统的文本压缩通常被视作标记删除、检索或精确重建。本文研究一种更激进但明确有损的设定：将文本压缩为紧凑编码，由大模型解码出任务相关的语义。我们称之为SemanticZip。不同于无损压缩，SemanticZip不要求字节级完全重建；不同于普通摘要，它将模型解码视为编解码器的一部分，并评估任务相关语义是否被恢复。本文是初步框架，非基准声明。我们形式化了基于大模型的解码机制，定义了受保护/有损数据包架构，并在五个自建诊断案例上评估六种表示方案：结构化散文、JSON、CCL-Core、CCL-Min、SemanticZip ASCII和SemanticZip emoji。独立解码器大模型从每种压缩表示中重构类型化的语义原子，评分包括关键原子召回率（Critical Atom Recall）、加权原子召回率（WAR）、精度和分词器收益。在本试验中，结构化散文恢复最佳，WAR=0.956，token gain达19.1%（o200k_base）。CCL-Min为最佳平衡点，压缩率39.4%，WAR=0.874。SemanticZip ASCII压缩最高效，达到46.5% token gain，WAR=0.802；而以表情符号为主的版本在压缩与恢复上均表现较差。主要贡献不在于这些数字构成通用前沿，而是提出可复现的实验接口，以及核心设计原则：安全关键与精确承诺应受保护，而可预测的低风险上下文可进行语义压缩。
原文摘要 · Abstract (English)
Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that an LLM can expand into task-relevant meaning. We call this setting SemanticZip. Unlike lossless compression, SemanticZip does not require byte-identical reconstruction; unlike ordinary summarization, it treats model-based decompression as part of the codec and evaluates whether task-relevant semantic commitments are recovered. This paper is a pilot framework, not a benchmark claim. We formalize LLM-mediated decompression, define a protected/lossy packet architecture, and evaluate six representation regimes over five author-constructed diagnostic cases: structured prose, JSON, CCL-Core, CCL-Min, SemanticZip ASCII, and SemanticZip emoji. An independent decoder LLM reconstructs typed semantic atoms from each compressed representation, and we score Critical Atom Recall, Weighted Atom Recall, precision, and tokenizer gain. In this pilot, structured prose has the highest recoverability, with WAR = 0.956 and 19.1% o200k_base token gain. CCL-Min is the strongest balanced point, with 39.4% token gain and WAR = 0.874. SemanticZip ASCII provides the largest useful compression, with 46.5% token gain and WAR = 0.802, while emoji-heavy SemanticZip performs worse on both compression and recovery. The main contribution is not the claim that these numbers establish a universal frontier. Rather, we introduce a reproducible experimental interface for studying lossy, LLM-decompressible text codes and a design principle: safety-critical and exact commitments should remain protected, while predictable low-risk context may be semantically zipped.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。