Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting
This work addresses the need for efficient prompt compression in LLM applications, offering a method that maintains high accuracy while reducing token usage, particularly beneficial for smaller models.
Telegraph English (TE) is a prompt-compression protocol that rewrites natural language into a structured symbolic dialect, achieving ~50% token reduction while preserving 99.1% accuracy on key facts with GPT-4.1 and outperforming LLMLingua-2 across all tested models and tasks, with up to 11 percentage point gains on smaller models.
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.