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 2409.17167cs.HCcs.AIcs.CL
收藏

StressPrompt:压力对大型语言模型和人类表现的影响相似吗?

StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Center for Long-term Artificial Intelligence(长期人工智能中心);School of Future Technology, University of Chinese Academy of Sciences(中国科学院大学未来技术学院)

Guobin Shen, Dongcheng Zhao, Aorigele Bao, Xiang He, Yiting Dong, Yi Zeng

AI总结:

本研究开发了StressPrompt提示集,探讨LLMs在不同压力提示下的表现,发现其在适度压力下性能最佳,符合Yerkes-Dodson定律,为AI系统在高压现实场景中的鲁棒性设计提供了新视角。

摘要:

人类经常会经历压力,这会显著影响他们的表现。本研究探讨大型语言模型(LLMs)是否表现出与人类相似的压力反应,以及它们在不同诱导压力的提示下性能是否会波动。为此,我们开发了一套名为StressPrompt的新型提示集,旨在诱导不同水平的压力。这些提示源自成熟的心理学框架,并根据人类参与者的评分进行了仔细校准。随后,我们将这些提示应用于多个LLMs,以评估它们在一系列任务中的表现,包括指令遵循、复杂推理和情感智力。研究结果表明,LLMs与人类一样,在适度压力下表现最佳,这与Yerkes-Dodson定律一致。值得注意的是,在低压力和高压力条件下,它们的性能都会下降。我们的分析进一步揭示,这些StressPrompts显著改变了LLMs的内部状态,导致其神经表征发生变化,这反映了人类对压力的反应。本研究为LLMs的运行鲁棒性和灵活性提供了关键见解,证明了设计能够在压力普遍存在的现实场景(如客户服务、医疗保健和应急响应环境)中保持高性能的AI系统的重要性。此外,本研究通过提供关于LLMs如何处理不同场景及其与人类认知相似性的新视角,为更广泛的AI研究社区做出了贡献。

英文摘要:

Human beings often experience stress, which can significantly influence their performance. This study explores whether Large Language Models (LLMs) exhibit stress responses similar to those of humans and whether their performance fluctuates under different stress-inducing prompts. To investigate this, we developed a novel set of prompts, termed StressPrompt, designed to induce varying levels of stress. These prompts were derived from established psychological frameworks and carefully calibrated based on ratings from human participants. We then applied these prompts to several LLMs to assess their responses across a range of tasks, including instruction-following, complex reasoning, and emotional intelligence. The findings suggest that LLMs, like humans, perform optimally under moderate stress, consistent with the Yerkes-Dodson law. Notably, their performance declines under both low and high-stress conditions. Our analysis further revealed that these StressPrompts significantly alter the internal states of LLMs, leading to changes in their neural representations that mirror human responses to stress. This research provides critical insights into the operational robustness and flexibility of LLMs, demonstrating the importance of designing AI systems capable of maintaining high performance in real-world scenarios where stress is prevalent, such as in customer service, healthcare, and emergency response contexts. Moreover, this study contributes to the broader AI research community by offering a new perspective on how LLMs handle different scenarios and their similarities to human cognition.

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。

↑