The Use of Generative Search Engines for Knowledge Work and Complex Tasks

TL;DR

This paper examines how generative search engines, like Bing Copilot, enable users to perform more complex knowledge work tasks by combining large language models with traditional search capabilities.

Contribution

It provides an empirical analysis of Bing Copilot, highlighting its use for higher-complexity tasks compared to traditional search engines.

Findings

Generative search engines are used for more cognitively complex tasks.

Users leverage Bing Copilot for knowledge work and complex problem-solving.

Generative search engines expand the scope of online information access.

Abstract

Until recently, search engines were the predominant method for people to access online information. The recent emergence of large language models (LLMs) has given machines new capabilities such as the ability to generate new digital artifacts like text, images, code etc., resulting in a new tool, a generative search engine, which combines the capabilities of LLMs with a traditional search engine. Through the empirical analysis of Bing Copilot (Bing Chat), one of the first publicly available generative search engines, we analyze the types and complexity of tasks that people use Bing Copilot for compared to Bing Search. Findings indicate that people use the generative search engine for more knowledge work tasks that are higher in cognitive complexity than were commonly done with a traditional search engine.