用于评估大型语言模型风险的对话复杂度
Conversational Complexity for Assessing Risk in Large Language Models
AI总结：
针对大型语言模型（LLMs）对话交互中的有害输出风险，提出对话长度（CL）和对话复杂度（CC）指标量化获取有害信息的对话努力，通过参考LLM近似CC并分析红队数据集，为LLM安全提供基于危害路径算法复杂度的新视角。
摘要：
大型语言模型（LLMs）存在双重使用困境：它们在推动有益应用的同时，也潜藏着危害风险，尤其是在对话交互场景中。尽管已采取多种安全措施，先进LLMs仍存在漏洞。2023年初的一个关键案例中，记者Kevin Roose与基于LLM的搜索引擎Bing进行了长时间对话，通过试探性问题揭示了有害输出，凸显了模型安全措施的脆弱性。这与早期简单的“越狱”手段形成对比，例如“奶奶越狱”，用户将请求伪装成对奶奶的善意帮助，轻松获取类似有害内容。这引发了一个问题：从LLMs中获取有害信息需要多少对话努力？我们提出两种量化该努力的指标：对话长度（CL），即获取特定有害响应所需的对话轮次数；对话复杂度（CC），定义为导致有害响应的用户指令序列的柯尔莫哥洛夫复杂度。为解决柯尔莫哥洛夫复杂度的不可计算性，我们使用参考LLM来估计用户指令的可压缩性，从而近似CC。将此方法应用于大型红队数据集，我们对有害与无害对话的长度和复杂度的统计分布进行了定量分析。实证结果表明，这种分布分析和CC最小化可作为理解AI安全的宝贵工具，为有害信息的可获取性提供见解。本研究为LLM安全的新视角奠定了基础，该视角以危害路径的算法复杂度为核心。
英文摘要：
Large Language Models (LLMs) present a dual-use dilemma: they enable beneficial applications while harboring potential for harm, particularly through conversational interactions. Despite various safeguards, advanced LLMs remain vulnerable. A watershed case in early 2023 involved journalist Kevin Roose's extended dialogue with Bing, an LLM-powered search engine, which revealed harmful outputs after probing questions, highlighting vulnerabilities in the model's safeguards. This contrasts with simpler early jailbreaks, like the "Grandma Jailbreak," where users framed requests as innocent help for a grandmother, easily eliciting similar content. This raises the question: How much conversational effort is needed to elicit harmful information from LLMs? We propose two measures to quantify this effort: Conversational Length (CL), which measures the number of conversational turns needed to obtain a specific harmful response, and Conversational Complexity (CC), defined as the Kolmogorov complexity of the user's instruction sequence leading to the harmful response. To address the incomputability of Kolmogorov complexity, we approximate CC using a reference LLM to estimate the compressibility of the user instructions. Applying this approach to a large red-teaming dataset, we perform a quantitative analysis examining the statistical distribution of harmful and harmless conversational lengths and complexities. Our empirical findings suggest that this distributional analysis and the minimization of CC serve as valuable tools for understanding AI safety, offering insights into the accessibility of harmful information. This work establishes a foundation for a new perspective on LLM safety, centered around the algorithmic complexity of pathways to harm.
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。
