Large Language Models vs. Search Engines: Evaluating User Preferences Across Varied Information Retrieval Scenarios

TL;DR

This study compares user preferences for search engines and large language models across various information retrieval scenarios, revealing patterns in tool preference based on query type and suggesting hybrid approaches.

Contribution

It provides a comprehensive analysis of user preferences between search engines and LLMs across diverse use cases, highlighting context-dependent choices and implications for future retrieval systems.

Findings

Users prefer search engines for factual queries

LLMs are favored for nuanced understanding tasks

Results suggest potential for hybrid retrieval models

Abstract

This study embarked on a comprehensive exploration of user preferences between Search Engines and Large Language Models (LLMs) in the context of various information retrieval scenarios. Conducted with a sample size of 100 internet users (N=100) from across the United States, the research delved into 20 distinct use cases ranging from factual searches, such as looking up COVID-19 guidelines, to more subjective tasks, like seeking interpretations of complex concepts in layman's terms. Participants were asked to state their preference between using a traditional search engine or an LLM for each scenario. This approach allowed for a nuanced understanding of how users perceive and utilize these two predominant digital tools in differing contexts. The use cases were carefully selected to cover a broad spectrum of typical online queries, thus ensuring a comprehensive analysis of user preferences. The findings reveal intriguing patterns in user choices, highlighting a clear tendency for participants to favor search engines for direct, fact-based queries, while LLMs were more often preferred for tasks requiring nuanced understanding and language processing. These results offer valuable insights into the current state of digital information retrieval and pave the way for future innovations in this field. This study not only sheds light on the specific contexts in which each tool is favored but also hints at the potential for developing hybrid models that leverage the strengths of both search engines and LLMs. The insights gained from this research are pivotal for developers, researchers, and policymakers in understanding the evolving landscape of digital information retrieval and user interaction with these technologies.