An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors and inhibits undesired ones, a process referred to as alignment. In this paper, we propose a theoretical approach called Behavior Expectation Bounds (BEB) which allows us to formally investigate several inherent characteristics and limitations of alignment in large language models. Importantly, we prove that within the limits of this framework, for any behavior that has a finite probability of being exhibited by the model, there exist prompts that can trigger the model into outputting this behavior, with probability that increases with the length of the prompt. This implies that any alignment process that attenuates an undesired behavior but does not remove it altogether, is not safe against adversarial prompting attacks. Furthermore, our framework hints at the mechanism by which leading alignment approaches such as reinforcement learning from human feedback make the LLM prone to being prompted into the undesired behaviors. This theoretical result is being experimentally demonstrated in large scale by the so called contemporary "chatGPT jailbreaks", where adversarial users trick the LLM into breaking its alignment guardrails by triggering it into acting as a malicious persona. Our results expose fundamental limitations in alignment of LLMs and bring to the forefront the need to devise reliable mechanisms for ensuring AI safety.

翻译：开发与人类交互的语言模型的一个重要方面是使其行为对用户既有用又无害。这一目标通常通过调整模型以增强期望行为并抑制非期望行为来实现，这一过程被称为对齐。本文提出了一种名为行为期望边界（Behavior Expectation Bounds, BEB）的理论方法，使我们能够从形式上研究大语言模型对齐的若干内在特性与局限性。重要的是，我们证明在该框架的范畴内，对于任何模型可能以有限概率展现的行为，都存在能够触发模型输出该行为的提示词，且触发概率随提示词长度增加而增大。这意味着任何削弱但未能彻底消除非期望行为的对齐过程，都无法抵御对抗性提示攻击。此外，我们的框架揭示了主流对齐方法（如基于人类反馈的强化学习）如何使大语言模型易被引导至非期望行为。这一理论结果已在当下被称为“ChatGPT越狱”的大规模实验中得到验证——对抗性用户通过触发大语言模型扮演恶意角色来突破其对齐护栏。我们的研究揭示了大语言模型对根本性的局限性，并凸显了设计可靠机制以确保人工智能安全的迫切需求。