We study context compression for multi-hop question answering with small language models. We propose Telegraph English, a readable symbolic format that rewrites retrieved passages into structured entity-relation statements, preserving reasoning evidence at lower token cost. In controlled experiments on MuSiQue, TwoWiki, and HotpotQA, Telegraph English outperforms three matched-budget compression baselines (character-level deletion, truncation, and random sub-sampling) on every dataset, with gains of 13 to 20 F1 percentage point. It also outperforms a coherent prose summary produced by the same encoder on the hardest dataset. A pre-registered depth-interaction hypothesis is null: the advantage does not grow with reasoning depth within datasets. We interpret these results as evidence that readable symbolic re-expression preserves entity content more densely than either natural language or coherent summarization at matched token budget.

翻译：我们研究了面向小型语言模型的多跳问答中的上下文压缩问题。我们提出“电报式英语”（Telegraph English），这是一种可读的符号化格式，能将检索到的段落重写为结构化的实体-关系陈述，在降低词元成本的同时保留推理证据。在MuSiQue、TwoWiki和HotpotQA的受控实验中，“电报式英语”在每个数据集上均优于三种匹配预算的压缩基线（字符级删除、截断和随机子采样），提升幅度达13至20个F1百分点。在最难的数据集上，它甚至优于同一编码器生成的连贯散文式摘要。一个预先注册的深度交互假设未被证实：其优势并不随数据集内的推理深度增加而增长。我们将这些结果解释为：在匹配词元预算下，可读的符号化重新表达比自然语言或连贯摘要更密集地保留了实体内容。