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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Sida, Swiatek, Wojciech, Gao, Allen, Cullivan, Paul, Chang, Haoge
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910304222314496
author Peng, Sida
Swiatek, Wojciech
Gao, Allen
Cullivan, Paul
Chang, Haoge
author_facet Peng, Sida
Swiatek, Wojciech
Gao, Allen
Cullivan, Paul
Chang, Haoge
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10956
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AI Revolution on Chat Bot: Evidence from a Randomized Controlled Experiment
Peng, Sida
Swiatek, Wojciech
Gao, Allen
Cullivan, Paul
Chang, Haoge
Human-Computer Interaction
Artificial Intelligence
Information Retrieval
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.
title AI Revolution on Chat Bot: Evidence from a Randomized Controlled Experiment
topic Human-Computer Interaction
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2401.10956