语言模型的目标选择与人类在自我指导学习任务中不同
Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task
AI总结:
研究通过控制实验发现语言模型在目标选择上与人类存在显著差异,多数模型表现不佳,而人类则能逐步探索并达成多样化目标。
摘要:
无论是在代理工作流程、社会研究还是聊天设置中,大型语言模型(LLMs)越来越多地被要求取代人类选择目标,而不是完成预定义任务。然而,LLMs准确反映人类目标选择偏好的假设尚未得到充分检验。我们评估了LLMs作为人类目标选择代理的有效性,采用来自认知科学的受控自我指导学习任务。在五个模型(GPT-5、Gemini 2.5 Pro、Claude Sonnet 4.5、Qwen3 32B和Centaur)中,发现显著偏离人类行为。尽管人们逐步探索并学习达成目标,具有多样性,但大多数模型倾向于单一解决方案或表现惊人低效,不同模型有不同模式,同一体系内的实例变化较小。链式推理和身份引导提供有限改进,结论在实验设置中保持一致。尽管在应用设置中有待确认,这些发现突显了人类目标选择的独特性,并警示当前模型不应被替代。
英文摘要:
Whether in agentic workflows, social studies, or chat settings, large language models (LLMs) are increasingly being asked to replace humans in choosing which goals to pursue, rather than completing predefined tasks. However, the assumption that LLMs accurately reflect human preferences for goal setting remains largely untested. We assess the validity of LLMs as proxies for human goal selection in a controlled, self-directed learning task borrowed from cognitive science. Across five models (GPT-5, Gemini 2.5 Pro, Claude Sonnet 4.5, Qwen3 32B, and Centaur), we find substantial divergence from human behavior. While people gradually explore and learn to achieve goals with diversity across individuals, most models exploit a single identified solution or show surprisingly low performance, with distinct patterns across models and little variability across instances of the same model. Chain-of-thought reasoning and persona steering provide limited improvements, and our conclusions hold across experimental settings. While they await confirmation in applied settings, these findings highlight the uniqueness of human goal selection and caution against its replacement with current models.
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。