CLNov 7, 2023

Do LLMs exhibit human-like response biases? A case study in survey design

CMU
arXiv:2311.04076v5186 citationsh-index: 51Has Code
AI Analysis

This work addresses the problem of using LLMs as proxies for humans in subjective tasks like surveys, highlighting pitfalls for researchers and practitioners, and is incremental in applying known social psychology concepts to AI evaluation.

The study investigated whether large language models (LLMs) exhibit human-like response biases in survey design, finding that popular open and commercial LLMs generally fail to reflect human-like behavior, particularly after RLHF, and are sensitive to perturbations that do not affect humans.

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 as proxies for humans in subjective tasks is their sensitivity to prompt wording - but interestingly, humans also display sensitivities to instruction changes in the form of response biases. We investigate the extent to which LLMs reflect human response biases, if at all. We look to survey design, where human response biases caused by changes in the wordings of "prompts" have been extensively explored in social psychology literature. Drawing from these works, we design a dataset and 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, particularly in models that have undergone RLHF. Furthermore, even if a model shows a significant change in the same direction as humans, we find that they are sensitive to perturbations that do not elicit significant changes in humans. These results highlight the pitfalls of using LLMs as human proxies, and underscore the need for finer-grained characterizations of model behavior. Our code, dataset, and collected samples are available at https://github.com/lindiatjuatja/BiasMonkey

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes