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

Korean

여러 대 언어 모델 (LLM)을 결합하는 시스템은 종종 여러 질문에 대해 하나의 컨텍스트를 사용합니다. 컨텍스트가 모델 간에 텍스트로 전달될 때, 수신 모델은 각 질문에 대해 다시 모든 토큰을 처리합니다.이 비용을 피하기 위해서는 컨텍스트 표현이 컴팩트하고 질문에 대해 재사용 가능하며 다른 LLM에 의해 읽을 수 있습니다. 기존 압축 및 잠재 커뮤니케이션 방법은 각각 이러한 특성 중 일부만을 제공합니다. 우리는 LatComm을 소개합니다. LatComm은 읽기와 코딩을 분리하여 세 가지를 제공하는 잠재 커뮤니케이션 인터페이스입니다. 컨텍스트는 질문없이 한 번 코딩됩니다. 수신자는 각 질문에 대해 무엇을 읽을 수 있는지 선택합니다. 얼어 붙은 컨텍스트 인코

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