English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Interactive user interfaces have increasingly explored AI's role in enhancingcommunication efficiency and productivity in collaborative tasks. The emergenceof Large Language Models (LLMs) such as ChatGPT has revolutionizedconversational agents, employing advanced deep learning techniques to generatecontext-aware, coherent, and personalized responses. Consequently, LLM-based AIassistants provide a more natural and efficient user experience across variousscenarios. In this paper, we study how LLM models can be used to improve workefficiency in collaborative workplaces. Specifically, we present an LLM-basedSmart Reply (LSR) system utilizing the ChatGPT to generate personalizedresponses in professional collaborative scenarios while adapting to context andcommunication style based on prior responses. Our two-step process involvesgenerating a preliminary response type (e.g., Agree, Disagree) to provide ageneralized direction for message generation, thus reducing response draftingtime. We conducted an experiment where participants completed simulated worktasks involving a Dual N-back test and subtask scheduling through GoogleCalendar while interacting with co-workers. Our findings indicate that theproposed LSR reduces overall workload, as measured by the NASA TLX, andimproves work performance and productivity in the N-back task. We also providequalitative analysis based on participants' experiences, as well as designconsiderations to provide future directions for improving such implementations.

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