Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting

• URL: http://arxiv.org/abs/2605.04426v1
• Date: Wed, 06 May 2026 02:40:55 GMT
• Title: Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting
• Abstract summary: We introduce a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect.<n>A consequence of the line-structure rule is that compression and semantic chunking become the same operation.<n>We evaluate TE on 4,081 question-answer pairs from LongBench-v2 across five OpenAI models and two difficulty levels.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• Context Compression Is Not One Thing: Readable Symbolic Re-expression vs. Coherent Summary at Matched Budget [0.0]
  We study context compression for multi-hop question answering with small language models.<n>We propose Telegraph English, a readable symbolic format that rewrites retrieved passages into structured entity-relation statements.<n>In controlled experiments on MuSiQue, TwoWiki, and HotpotQA, Telegraph English outperforms three matched-budget compression baselines.
  arXiv  Detail & Related papers  (2026-06-12T18:27:23Z)
• Mapping Text to Multiplex Graph: Prompt Compression as Lévy Walk-Guided Graph Pruning [55.43705665875779]
  RAGP formulates prompt compression as Redundancy-Aware Graph Pruning on a multiplex graph.<n> Experiments on LongBench show that RAGP achieves an average score of 49.3 under a 4x compression ratio.
  arXiv  Detail & Related papers  (2026-05-04T01:41:31Z)
• Compute Optimal Tokenization [79.3815358070537]
  We investigate how the information granularity of tokens, controlled by the compression rate, affects scaling trends.<n>We train 988 latent tokenized models (BLT) ranging from 50M to 7B parameters that enable setting the desired compression rate.<n>Our experiments reveal that in compute-optimal configurations, model parameter counts scale proportionally to data size measured in bytes, not in tokens as commonly perceived.
  arXiv  Detail & Related papers  (2026-05-02T01:53:22Z)
• <SOG_k>: One LLM Token for Explicit Graph Structural Understanding [57.017902343605364]
  We propose to incorporate one special token SOG_k> to fully represent the Structure Of Graph within a unified token space.<n>SOG_k> empowers LLMs to understand, generate, and reason in a concise and accurate manner.
  arXiv  Detail & Related papers  (2026-02-02T07:55:09Z)
• Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method [0.0]
  We introduce a novel (patent pending) text representation scheme and a first-of-its-kind word-level semantic compression of paragraphs.<n>We show how our results hold at the paragraph level, across multiple genres and models.
  arXiv  Detail & Related papers  (2025-05-12T20:49:50Z)
• Discourse Features Enhance Detection of Document-Level Machine-Generated Content [53.41994768824785]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>Existing MGC detectors often focus solely on surface-level information, overlooking implicit and structural features.<n>We introduce novel methodologies and datasets to overcome these challenges.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• MrT5: Dynamic Token Merging for Efficient Byte-level Language Models [50.46453950887946]
  This work introduces MrT5 (MergeT5), a more efficient variant of ByT5 that integrates a token deletion mechanism in its encoder to dynamically shorten the input sequence length.<n>MrT5 effectively "merges" critical information from deleted tokens into a more compact sequence, leveraging contextual information from the remaining tokens.<n>MrT5 shows comparable accuracy to ByT5 on downstream evaluations such as XNLI, TyDi QA, and character-level tasks while reducing sequence lengths by up to 75%.
  arXiv  Detail & Related papers  (2024-10-28T06:14:12Z)
• Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles [49.65811277223873]
  Style-Compress is a lightweight framework that adapts a smaller language model to compress prompts for a larger model on a new task without additional training. Our approach iteratively generates and selects effective compressed prompts as task-specific demonstrations through style variation and in-context learning. Style-Compress outperforms two baseline compression models in four tasks: original prompt reconstruction, text summarization, multi-hop QA, and CoT reasoning.
  arXiv  Detail & Related papers  (2024-10-17T21:35:49Z)
• LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression [43.048684907893104]
  This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. We formulate prompt compression as a token classification problem to guarantee the faithfulness of the compressed prompt to the original one. Our approach leads to lower latency by explicitly learning the compression objective with smaller models such as XLM-RoBERTa-large and mBERT.
  arXiv  Detail & Related papers  (2024-03-19T17:59:56Z)
• Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance [34.641079276516926]
  We argue for the theoretical importance of compression, that can be viewed as 0-gram language modeling. We demonstrate the empirical importance of compression for downstream success of pre-trained language models. We show that there is a correlation between tokenizers' compression and models' downstream performance.
  arXiv  Detail & Related papers  (2024-03-10T17:02:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.