Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review

TL;DR

This paper systematically reviews 153 CHI papers from 2020-24 to understand how large language models are being integrated into HCI research, highlighting applications, roles, and challenges.

Contribution

It provides a comprehensive taxonomy of LLM use in HCI, analyzing domains, roles, contributions, and limitations, offering guidance for future research.

Findings

LLMs are applied across 10 diverse HCI domains.

Authors use LLMs mainly as research tools or simulated users.

Concerns about validity, reproducibility, and focus on closed models are prevalent.

Abstract

Large language models (LLMs) have been positioned to revolutionize HCI, by reshaping not only the interfaces, design patterns, and sociotechnical systems that we study, but also the research practices we use. To-date, however, there has been little understanding of LLMs' uptake in HCI. We address this gap via a systematic literature review of 153 CHI papers from 2020-24 that engage with LLMs. We taxonomize: (1) domains where LLMs are applied; (2) roles of LLMs in HCI projects; (3) contribution types; and (4) acknowledged limitations and risks. We find LLM work in 10 diverse domains, primarily via empirical and artifact contributions. Authors use LLMs in five distinct roles, including as research tools or simulated users. Still, authors often raise validity and reproducibility concerns, and overwhelmingly study closed models. We outline opportunities to improve HCI research with and on LLMs, and provide guiding questions for researchers to consider the validity and appropriateness of LLM-related work.