LLM-based Smart Reply (LSR): Enhancing Collaborative Performance with ChatGPT-mediated Smart Reply System

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bastola, Ashish, Wang, Hao, Hembree, Judsen, Yadav, Pooja, Gong, Zihao, Dixon, Emma, Razi, Abolfazl, McNeese, Nathan
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914701478199296
author Bastola, Ashish
Wang, Hao
Hembree, Judsen
Yadav, Pooja
Gong, Zihao
Dixon, Emma
Razi, Abolfazl
McNeese, Nathan
author_facet Bastola, Ashish
Wang, Hao
Hembree, Judsen
Yadav, Pooja
Gong, Zihao
Dixon, Emma
Razi, Abolfazl
McNeese, Nathan
contents Interactive user interfaces have increasingly explored AI's role in enhancing communication efficiency and productivity in collaborative tasks. The emergence of Large Language Models (LLMs) such as ChatGPT has revolutionized conversational agents, employing advanced deep learning techniques to generate context-aware, coherent, and personalized responses. Consequently, LLM-based AI assistants provide a more natural and efficient user experience across various scenarios. In this paper, we study how LLM models can be used to improve work efficiency in collaborative workplaces. Specifically, we present an LLM-based Smart Reply (LSR) system utilizing the ChatGPT to generate personalized responses in professional collaborative scenarios while adapting to context and communication style based on prior responses. Our two-step process involves generating a preliminary response type (e.g., Agree, Disagree) to provide a generalized direction for message generation, thus reducing response drafting time. We conducted an experiment where participants completed simulated work tasks involving a Dual N-back test and subtask scheduling through Google Calendar while interacting with co-workers. Our findings indicate that the proposed LSR reduces overall workload, as measured by the NASA TLX, and improves work performance and productivity in the N-back task. We also provide qualitative analysis based on participants' experiences, as well as design considerations to provide future directions for improving such implementations.
format Preprint
id arxiv_https___arxiv_org_abs_2306_11980
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LLM-based Smart Reply (LSR): Enhancing Collaborative Performance with ChatGPT-mediated Smart Reply System
Bastola, Ashish
Wang, Hao
Hembree, Judsen
Yadav, Pooja
Gong, Zihao
Dixon, Emma
Razi, Abolfazl
McNeese, Nathan
Human-Computer Interaction
Interactive user interfaces have increasingly explored AI's role in enhancing communication efficiency and productivity in collaborative tasks. The emergence of Large Language Models (LLMs) such as ChatGPT has revolutionized conversational agents, employing advanced deep learning techniques to generate context-aware, coherent, and personalized responses. Consequently, LLM-based AI assistants provide a more natural and efficient user experience across various scenarios. In this paper, we study how LLM models can be used to improve work efficiency in collaborative workplaces. Specifically, we present an LLM-based Smart Reply (LSR) system utilizing the ChatGPT to generate personalized responses in professional collaborative scenarios while adapting to context and communication style based on prior responses. Our two-step process involves generating a preliminary response type (e.g., Agree, Disagree) to provide a generalized direction for message generation, thus reducing response drafting time. We conducted an experiment where participants completed simulated work tasks involving a Dual N-back test and subtask scheduling through Google Calendar while interacting with co-workers. Our findings indicate that the proposed LSR reduces overall workload, as measured by the NASA TLX, and improves work performance and productivity in the N-back task. We also provide qualitative analysis based on participants' experiences, as well as design considerations to provide future directions for improving such implementations.
title LLM-based Smart Reply (LSR): Enhancing Collaborative Performance with ChatGPT-mediated Smart Reply System
topic Human-Computer Interaction
url https://arxiv.org/abs/2306.11980