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. While
the state-of-the-art LLM debate methods using natural language outperforms
traditional inference by a margin of 1.5-8%, our experiment results show that
CIPHER debate further extends this lead by 1-3.5% 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.

通过引入名为 CIPHER 的通信机制，本文通过使用嵌入表示的期望而不是自然语言的方式，无需修改模型权重即可将更广泛的信息编码进大型语言模型之间的通信，实验证明 CIPHER 辩论方法在多项推理任务中取得了相对于传统推理方法 1-3.5% 的性能提升，展示了嵌入表示作为大型语言模型间交流的替代 “语言” 的优势和鲁棒性。

让模型发表言论：通过嵌入进行多智能体辩论

Let Models Speak Ciphers: Multiagent Debate through Embeddings

Safety lies at the core of the development of Large Language Models (LLMs).
There is ample work on aligning LLMs with human ethics and preferences,
including data filtering in pretraining, supervised fine-tuning, reinforcement
learning from human feedback, and red teaming, etc. In this study, we discover
that chat in cipher can bypass the safety alignment techniques of LLMs, which
are mainly conducted in natural languages. We propose a novel framework
CipherChat to systematically examine the generalizability of safety alignment
to non-natural languages -- ciphers. CipherChat enables humans to chat with
LLMs through cipher prompts topped with system role descriptions and few-shot
enciphered demonstrations. We use CipherChat to assess state-of-the-art LLMs,
including ChatGPT and GPT-4 for different representative human ciphers across
11 safety domains in both English and Chinese. Experimental results show that
certain ciphers succeed almost 100% of the time to bypass the safety alignment
of GPT-4 in several safety domains, demonstrating the necessity of developing
safety alignment for non-natural languages. Notably, we identify that LLMs seem
to have a ''secret cipher'', and propose a novel SelfCipher that uses only role
play and several demonstrations in natural language to evoke this capability.
SelfCipher surprisingly outperforms existing human ciphers in almost all cases.
Our code and data will be released at this https URL

通过 CipherChat 框架评估 ChatGPT 和 GPT-4，发现某些密码能够在多个安全领域中以近乎 100% 的成功率绕过 GPT-4 的安全对齐，证明了开发非自然语言安全对齐的必要性，同时提出了一种新颖的 SelfCipher 方法，在几乎所有情况下表现优于现有的人工密码。