Scholarlink

<p>Large language models (LLMs) have been increasingly used to simulate human behaviour because of their ability to generate contextually coherent dialogues. Such abilities can enhance the realism of models. However, the pursuit of realism is not necessarily compatible with the epistemic foundation of modelling. We explore when LLM agents can be too ‘human’ to model, i.e., when they are too expressive, detailed and intractable to be consistent with the abstraction, simplification, and interpretability typically demanded by modelling. Through a model-building thought experiment, we uncover five core dilemmas: a temporal resolution mismatch between natural conversation and abstract time steps; the need for intervention in agent conversations without undermining spontaneous outputs; the temptation to introduce rules while maintaining conversational naturalness; the tension between role consistency and role evolution; and the challenge of understanding emergence. These dilemmas lead LLM agents to an “uncanny valley”: more realistic than rule-based agents but recognisably unhuman.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Too human to model: the uncanny valley of large language models in simulating human systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月2日

查看全文
  • Yongchao Zeng,
  • Calum Brown,
  • Mark Rounsevell

摘要

Large language models (LLMs) have been increasingly used to simulate human behaviour because of their ability to generate contextually coherent dialogues. Such abilities can enhance the realism of models. However, the pursuit of realism is not necessarily compatible with the epistemic foundation of modelling. We explore when LLM agents can be too ‘human’ to model, i.e., when they are too expressive, detailed and intractable to be consistent with the abstraction, simplification, and interpretability typically demanded by modelling. Through a model-building thought experiment, we uncover five core dilemmas: a temporal resolution mismatch between natural conversation and abstract time steps; the need for intervention in agent conversations without undermining spontaneous outputs; the temptation to introduce rules while maintaining conversational naturalness; the tension between role consistency and role evolution; and the challenge of understanding emergence. These dilemmas lead LLM agents to an “uncanny valley”: more realistic than rule-based agents but recognisably unhuman.