arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.03303cs.CLcs.AIcs.LG
收藏

别管它:大型语言模型中的指令覆盖与审核

Nevermind: Instruction Override and Moderation in Large Language Models

Drexel University(德雷塞尔大学)

Edward Kim

AI总结:

本研究基准测试了不同规模LLM在冲突情境下的指令遵循能力,发现较大模型表现最佳,但改进指令遵循与安全过滤相矛盾,提出安全措施应外部化。

摘要:

鉴于近期大型语言模型(LLMs)的显著能力,我们研究并基准测试了最流行的专有模型以及不同规模的开源模型在冲突情境(例如覆盖)下明确指令遵循的任务。这些包括模型覆盖其权重内知识的能力、覆盖(或审核)提示中提取知识的能力,以及最后执行完全越狱的能力。进行的实验表明,有几个关键发现可以改进指令遵循——较大的模型在遵循覆盖内部和上下文指令方面表现最佳,并且即使有缺陷也表现出顺从。当通过rope scaling扩展到更长的上下文时,需要从困惑度悬崖边缘保持一个显著的缓冲区,以维持指令遵循能力。最后,我们观察到改进指令遵循,以及随后的指令覆盖/越狱,从根本上与语言模型遵循给定安全过滤器或指南的能力相矛盾。因此,我们假设实现安全、可信赖AI的最有效方法应在LLM本身之外处理。

英文摘要:

Given the impressive capabilities of recent Large Language Models (LLMs), we investigate and benchmark the most popular proprietary and different sized open source models on the task of explicit instruction following in conflicting situations, e.g. overrides. These include the ability of the model to override the knowledge within the weights of the model, the ability to override (or moderate) extracted knowledge in the prompt, and lastly the ability to perform a full jailbreak. Experimentation performed suggest several key findings to improve instruction following - larger models perform the best in following instructions that override internal and contextual instructions, and are obedient, even to a fault. When scaling to longer contexts via rope scaling, a significant buffer needs to be maintained from the edge of the perplexity cliff in order to maintain instruction following capabilities. Finally, we observe improving instruction following, and subsequently instruction overrides/jailbreaks, is fundamentally at odds with the ability of a language model to follow given safety filters or guidelines. Thus, we postulate the most effective approach for safe, trustworthy AI should be dealt external to the LLM itself.

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。

↑