让大模型通过共享缓存空间直接交流，提升协作效率与性能。
Latent Space Communication via K-V Cache Alignment
- 用适配器对齐多模型的k-v缓存，构建共享状态空间。
- 实验显示协作通信提升模型性能，且可迁移软提示等技能。
- 适合研究多模型协作、高效知识共享的学者与工程师。
解决大型语言模型（LLMs）日益复杂的任务需要超越单个模型，转向能有效协作的多模型系统。尽管传统上以文本作为模型间通信媒介，但若模型能直接访问彼此内部状态，则可实现更丰富高效的交互。本文提出一种学习共享表示空间的方法，对齐多个模型的k-v缓存，从而在不修改预训练参数的前提下，建立高带宽协作通道。通过为每个模型添加适配器，实现其状态在共享空间中的转换。在Gemma-2模型上的系列实验表明，该方法不仅支持无缝模型间通信，还提升了个体模型表现，并可直接传递软提示等已学技能。本工作为模型间流畅共享知识与能力的未来迈出关键一步。
原文摘要 · Abstract (English)
Solving increasingly complex problems with large language models (LLMs) necessitates a move beyond individual models and towards multi-model systems that can effectively collaborate. While text has traditionally served as the medium for inter-model communication, a richer and more efficient exchange is possible if models can access each other's internal states directly. In this paper, we propose learning a shared representation space that aligns the k-v caches of multiple models, creating a high-bandwidth channel for collaboration without altering the underlying pre-trained parameters. We do so by augmenting each model with adapters to translate its state into and out of this shared space. Via a suite of experiments with Gemma-2 models, we demonstrate that this approach not only enables seamless inter-model communication but also improves individual model performance. We also show that the shared space allows for the direct transfer of learned skills, such as soft prompts, between different models. Our work represents a significant step towards a future where models can fluidly share knowledge and capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。