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 2407.01505cs.CLcs.AI
收藏

大型语言模型中的自我认知:一项探索性研究

Self-Cognition in Large Language Models: An Exploratory Study

Huazhong University of Science and Technology(华中科技大学);Duke University(杜克大学);Lehigh University(里海大学)

Dongping Chen, Jiawen Shi, Yao Wan, Pan Zhou, Neil Zhenqiang Gong, Lichao Sun

AI总结:

本文首次系统探索大型语言模型的自我认知,通过构建提示池和量化原则发现4个模型具有可检测的自我认知,并揭示其与模型规模、数据质量正相关,且能增强创意写作等任务。

摘要:

尽管大型语言模型(LLMs)在各种应用中取得了显著成功,但它们也引发了关于自我认知的担忧。在本文中,我们开展了一项开创性研究,以探索LLMs中的自我认知。具体来说,我们首先构建了一个自我认知指令提示池,用于评估LLM在何处表现出自我认知,并提出了四条精心设计的原则来量化LLMs的自我认知。我们的研究揭示,在Chatbot Arena上的48个模型中,有4个模型——具体为Command R、Claude3-Opus、Llama-3-70b-Instruct和Reka-core——表现出一定程度的可检测自我认知。我们观察到模型规模、训练数据质量与自我认知水平之间存在正相关关系。此外,我们还探索了LLM在自我认知状态下的效用和可信度,揭示出自我认知状态会增强某些特定任务,如创意写作和夸张表达。我们相信,我们的工作可以为进一步研究LLMs中的自我认知提供启发。

英文摘要:

While Large Language Models (LLMs) have achieved remarkable success across various applications, they also raise concerns regarding self-cognition. In this paper, we perform a pioneering study to explore self-cognition in LLMs. Specifically, we first construct a pool of self-cognition instruction prompts to evaluate where an LLM exhibits self-cognition and four well-designed principles to quantify LLMs' self-cognition. Our study reveals that 4 of the 48 models on Chatbot Arena--specifically Command R, Claude3-Opus, Llama-3-70b-Instruct, and Reka-core--demonstrate some level of detectable self-cognition. We observe a positive correlation between model size, training data quality, and self-cognition level. Additionally, we also explore the utility and trustworthiness of LLM in the self-cognition state, revealing that the self-cognition state enhances some specific tasks such as creative writing and exaggeration. We believe that our work can serve as an inspiration for further research to study the self-cognition in LLMs.

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。

↑