让模型说密语：通过嵌入进行多智能体辩论
Let Models Speak Ciphers: Multiagent Debate through Embeddings
AI总结：
本文提出CIPHER通信机制，通过去除token采样步骤、直接使用transformer输出嵌入的期望值进行LLM间辩论通信，在多个推理任务上比自然语言辩论方法性能提升0.5-5.0%，展示了嵌入作为LLM间通信替代语言的优越性。
摘要：
大型语言模型（LLMs）之间的讨论与辩论因其增强LLMs推理能力的潜力而受到广泛关注。尽管由于LLMs的语言理解能力，自然语言是通信的显然选择，但在生成自然语言时所需的token采样步骤带来了潜在的信息损失风险，因为它仅使用一个token来表示模型在整个词汇表上的信念。在本文中，我们引入了一种名为CIPHER（通过嵌入表示进行的模型间通信协议）的通信机制来解决这一问题。具体而言，我们去除了LLMs中的token采样步骤，让它们通过原始transformer输出嵌入的期望值在整个词汇表上传递其信念。值得注意的是，通过偏离自然语言，CIPHER具有在不修改模型权重的情况下编码更广泛信息谱系的优势，在五个推理任务和多个不同规模的开源LLMs上，比使用自然语言的最先进LLM辩论方法性能高出0.5-5.0%。这展示了嵌入作为LLMs之间通信的替代“语言”的优越性和鲁棒性。我们预期CIPHER将激发对LLM智能体系统内部交互设计的进一步探索，为可能显著影响该领域未来发展的新方向提供启示。
英文摘要：
Discussion and debate among Large Language Models (LLMs) have gained considerable attention due to their potential to enhance the reasoning ability of LLMs. Although natural language is an obvious choice for communication due to LLM's language understanding capability, the token sampling step needed when generating natural language poses a potential risk of information loss, as it uses only one token to represent the model's belief across the entire vocabulary. In this paper, we introduce a communication regime named CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. Specifically, we remove the token sampling step from LLMs and let them communicate their beliefs across the vocabulary through the expectation of the raw transformer output embeddings. Remarkably, by deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights, outperforming the state-of-the-art LLM debate methods using natural language by 0.5-5.0% across five reasoning tasks and multiple open-source LLMs of varying sizes. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs. We anticipate that CIPHER will inspire further exploration for the design of interactions within LLM agent systems, offering a new direction that could significantly influence future developments in the field.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
