Newest papers

LatComm: Reusable Context Compression for Latent Communication between Large Language Models

Huawei Lin, Jinting Liu, Tan Yu, Weijie Zhao · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26840 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

ويستخدم النظامون الذين يجمعون عدة نموذج لغة كبيرة (LLMs) في كثير من الأحيان سياق واحد للعديد من الأسئلة. عندما يتم نقل سياق بين النماذج مثل النص، يقوم نموذج المشتري بإجراء جميع تقييماتهم مرة أخرى لكل الأسئلة. تجنب هذا التكاليف، يتطلب عرض سياق متكامل، يمكن الاستفادة منه في جميع الأسئلة، ويمكن قراءته من قبل LLM مختلف. تقييم سياق متكامل متكامل ووسائل الاتصال المتوفرة كلها توفر فقط بعض من هذه الخصائص. نحن نقدم LatComm، رابط الاتصال المتكرر الذي يوفر كل منها عن طريق تقييم متكرر: يتم تقييم سياق واحد بدون الأسئلة، ويختار المشتري ما

Machine translation (Meta M2M100); the English original follows.

Abstract

Systems that combine several large language models (LLMs) often use one context for many questions. When the context is passed between models as text, the receiving model processes all of its tokens again for every question. Avoiding this cost requires a context representation that is compact, reusable across questions, and readable by a different LLM. Existing compression and latent communication methods each provide only some of these properties. We introduce LatComm, a Latent Communication interface that provides all three by separating encoding from reading: the context is encoded once without the question, and the receiver selects what to read for each question. A frozen context encoder LLM compresses the context into a fixed-size packet and sends it to a different frozen receiver LLM, which reads the packet through cross-attention, with gates computed from its prompt. On 12 multiple-choice question-answering datasets, LatComm improves average accuracy over single-vector baselines by up to 10.2 points. On QuALITY, it reduces the receiver's input by 57x and answers the questions of an article 3x faster.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Context (archaeology), Encoding (memory), Context model, Network packet, Language model

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange