解题效率和指令情感对人类和GPT-4加法与减法解题策略的影响
Influence of Solution Efficiency and Valence of Instruction on Additive and Subtractive Solution Strategies in Humans and GPT-4
AI总结:
本研究发现GPT-4在解题效率和指令情感影响下表现出更强的加法倾向,而人类在减法更高效时更少使用加法策略。
摘要:
生成式人工智能,特别是大语言模型(LLMs),在人类决策情境中扮演着越来越重要的角色,需要对其能力具有透明度。尽管先前研究已显示人类存在加法偏差(Adams等,2021)和OpenAI的GPT-3(Winter等,2023),本研究通过比较人类和GPT-4在空间和语言任务中的问题解决能力,扩展了相关研究,任务中存在解题效率和任务指令情感的变化。四个预注册实验涉及588名来自美国的参与者和680次GPT-4迭代,结果显示GPT-4比人类更倾向于使用加法转换。人类参与者在减法相对更高效时使用加法策略的可能性较低,而在加法和减法同样高效时则较低。GPT-4则表现出相反的行为,当减法更高效时,其使用加法策略的倾向更强。在任务指令的情感方面,GPT-4在被要求“改进”(积极)而非“编辑”(中性)时,使用加法策略的频率增加。这些发现表明,人类问题解决中的偏差在GPT-4中被放大,且LLM的行为与基于效率的人类策略不同。这突显了LLM的局限性,并强调了在现实应用中使用它们时需要谨慎。
英文摘要:
Generative artificial intelligences, particularly large language models (LLMs), play an increasingly prominent role in human decision-making contexts, necessitating transparency about their capabilities. While prior studies have shown addition biases in humans (Adams et al., 2021) and OpenAI's GPT-3 (Winter et al., 2023), this study extends the research by comparing human and GPT-4 problem-solving across both spatial and linguistic tasks, with variations in solution efficiency and valence of task instruction. Four preregistered experiments with 588 participants from the U.S. and 680 GPT-4 iterations revealed a stronger tendency towards additive transformations in GPT-4 than in humans. Human participants were less likely to use additive strategies when subtraction was relatively more efficient than when addition and subtraction were equally efficient. GPT-4 exhibited the opposite behavior, with a strong addition bias when subtraction was more efficient. In terms of valence of task instruction, GPT-4's use of additive strategies increased when instructed to "improve" (positive) rather than "edit" (neutral). These findings demonstrate that biases in human problem-solving are amplified in GPT-4, and that LLM behavior differs from human efficiency-based strategies. This highlights the limitations of LLMs and the need for caution when using them in real-world applications.
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。