English

AI Revolution on Chat Bot: Evidence from a Randomized Controlled Experiment

Human-Computer Interaction 2024-01-23 v1 Artificial Intelligence Information Retrieval

Abstract

In recent years, generative AI has undergone major advancements, demonstrating significant promise in augmenting human productivity. Notably, large language models (LLM), with ChatGPT-4 as an example, have drawn considerable attention. Numerous articles have examined the impact of LLM-based tools on human productivity in lab settings and designed tasks or in observational studies. Despite recent advances, field experiments applying LLM-based tools in realistic settings are limited. This paper presents the findings of a field randomized controlled trial assessing the effectiveness of LLM-based tools in providing unmonitored support services for information retrieval.

Keywords

Cite

@article{arxiv.2401.10956,
  title  = {AI Revolution on Chat Bot: Evidence from a Randomized Controlled Experiment},
  author = {Sida Peng and Wojciech Swiatek and Allen Gao and Paul Cullivan and Haoge Chang},
  journal= {arXiv preprint arXiv:2401.10956},
  year   = {2024}
}
R2 v1 2026-06-28T14:22:02.507Z