LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs
Abstract
LLMs have shown promise in replicating human-like behavior in crowdsourcing tasks that were previously thought to be exclusive to human abilities. However, current efforts focus mainly on simple atomic tasks. We explore whether LLMs can replicate more complex crowdsourcing pipelines. We find that modern LLMs can simulate some of crowdworkers' abilities in these ``human computation algorithms,'' but the level of success is variable and influenced by requesters' understanding of LLM capabilities, the specific skills required for sub-tasks, and the optimal interaction modality for performing these sub-tasks. We reflect on human and LLMs' different sensitivities to instructions, stress the importance of enabling human-facing safeguards for LLMs, and discuss the potential of training humans and LLMs with complementary skill sets. Crucially, we show that replicating crowdsourcing pipelines offers a valuable platform to investigate 1) the relative LLM strengths on different tasks (by cross-comparing their performances on sub-tasks) and 2) LLMs' potential in complex tasks, where they can complete part of the tasks while leaving others to humans.
Cite
@article{arxiv.2307.10168,
title = {LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs},
author = {Tongshuang Wu and Haiyi Zhu and Maya Albayrak and Alexis Axon and Amanda Bertsch and Wenxing Deng and Ziqi Ding and Bill Guo and Sireesh Gururaja and Tzu-Sheng Kuo and Jenny T. Liang and Ryan Liu and Ihita Mandal and Jeremiah Milbauer and Xiaolin Ni and Namrata Padmanabhan and Subhashini Ramkumar and Alexis Sudjianto and Jordan Taylor and Ying-Jui Tseng and Patricia Vaidos and Zhijin Wu and Wei Wu and Chenyang Yang},
journal= {arXiv preprint arXiv:2307.10168},
year = {2025}
}