用符号化结构重写提示词，实现高效语义压缩。
Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting
- 将自然语言拆解为原子事实行，用约40种逻辑符号替代冗长表达。
- 在约50%令牌减少下，保持GPT-4.1 99.1%的关键事实准确率。
- 适合需要轻量级高精度推理的场景，尤其对小模型提升显著。
我们提出Telegraph English（TE），一种将自然语言重写为符号丰富、形式化结构化方言的提示压缩协议。与固定比例删除低重要性令牌的方法（如LLMLingua-2）不同，TE执行完整的语义重写：将输入分解为原子事实行，用约40个逻辑与关系符号替换冗长短语，并使压缩比随文档信息密度自适应调整。线性结构规则使压缩与语义分块合二为一——每行输出均为可独立定位的事实，因此压缩结果同时充当语义索引。我们在LongBench-v2的4,081个问答对上评估了五个OpenAI模型和两种难度级别。在约50%的令牌减少下，TE在GPT-4.1上保留99.1%的关键事实准确率，且在所有模型与任务中均优于等压缩比下的LLMLingua-2；在小模型上的差距更达11个百分点，表明显式关系结构可有效弥补模型容量不足。我们已公开语法规范、压缩提示、基准数据与参考实现。
原文摘要 · Abstract (English)
We introduce Telegraph English (TE), a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect. Where token-deletion methods such as LLMLingua-2 train a classifier to delete low-importance tokens at a fixed ratio, TE performs a full semantic rewrite: it decomposes the input into atomic fact lines, substitutes verbose phrases with $\sim$40 logical and relational symbols, and lets the compression ratio adapt to each document's information density. A consequence of the line-structure rule is that compression and semantic chunking become the same operation -- each output line is an independently addressable fact, so the compressed representation is simultaneously a semantic index. We evaluate TE on 4{,}081 question-answer pairs from LongBench-v2 across five OpenAI models and two difficulty levels. At roughly 50\% token reduction, TE preserves 99.1\% accuracy on key facts with GPT-4.1 and outperforms LLMLingua-2 at matched compression ratios on every model and task tested. The gap widens on smaller models -- up to 11 percentage points on fine-detail tasks -- suggesting that explicit relational structure compensates for limited model capacity. We release the grammar specification, compression prompt, benchmark data, and reference implementation.
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。