LatComm 提出潜在通信方法：上下文压缩一次可跨 LLM 复用
LatComm: Reusable Context Compression for Latent Communication between Large Language Models
多模型协作时上下文要反复处理，这篇论文的 LatComm 压缩一次就能复用，QuALITY 上输入省了 57 倍，速度还快 3 倍。
arXiv 论文提出 LatComm，一种 LLM 之间的潜在通信接口，核心是把上下文编码与读取分离。冻结的编码器 LLM 将上下文压缩成固定大小的数据包，接收方 LLM 通过 cross-attention 并按问题计算门控来选择性读取，无需重新处理全部文本。在 12 个多项选择问答数据集上，LatComm 的平均准确率比单向量基线最高提升 10.2 个百分点。在 QuALITY 基准上，接收方的输入量减少 57 倍，回答同一篇文章的多个问题时速度提升 3 倍。
LatComm: Reusable Context Compression for Latent Communication between Large Language Models
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.