As large language models (LLMs) become more capable, there is growing excitement about the possibility of using LLMs as proxies for humans in real-world tasks where subjective labels are desired, such as in surveys and opinion polling. One widely-cited barrier to the adoption of LLMs is their sensitivity to prompt wording - but interestingly, humans also display sensitivities to instruction changes in the form of response biases. As such, we argue that if LLMs are going to be used to approximate human opinions, it is necessary to investigate the extent to which LLMs also reflect human response biases, if at all. In this work, we use survey design as a case study, where human response biases caused by permutations in wordings of "prompts" have been extensively studied. Drawing from prior work in social psychology, we design a dataset and propose a framework to evaluate whether LLMs exhibit human-like response biases in survey questionnaires. Our comprehensive evaluation of nine models shows that popular open and commercial LLMs generally fail to reflect human-like behavior. These inconsistencies tend to be more prominent in models that have been instruction fine-tuned. Furthermore, even if a model shows a significant change in the same direction as humans, we find that perturbations that are not meant to elicit significant changes in humans may also result in a similar change. These results highlight the potential pitfalls of using LLMs to substitute humans in parts of the annotation pipeline, and further underscore the importance of finer-grained characterizations of model behavior. Our code, dataset, and collected samples are available at https://github.com/lindiatjuatja/BiasMonkey

翻译：随着大语言模型能力的提升，利用其替代人类完成需要主观标签的现实任务（如调查和民意测验）的可能性日益受到关注。一个常被提及的采用障碍是模型对提示词措辞的敏感性——但有趣的是，人类同样会因指令变化而表现出回答偏差。因此，我们认为若要将LLMs用于近似人类观点，研究其是否及在多大程度上反映人类回答偏差至关重要。本研究以调查设计为案例——该领域已深入探讨人类因"提示语"措辞变化而产生的回答偏差。基于社会心理学先验研究，我们构建数据集并提出评估框架，检验LLMs在调查问卷中是否呈现类似人类的回答偏差。对九种模型的全面评估表明，主流开源与商业LLMs普遍未能复现人类行为特征，且指令微调模型的这种不一致性尤为显著。更关键的是，即使模型在与人类同方向变化时表现出显著性差异，那些通常不会引发人类显著变化的扰动，也可能导致模型产生类似变化。这些结果揭示了LLMs替代人类参与标注流程的潜在陷阱，进一步凸显了精细刻画模型行为特征的重要性。相关代码、数据集及采集样本已开源至https://github.com/lindiatjuatja/BiasMonkey