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

2025-01-22

AI Summary

Despite growing adoption of large language models (LLMs) in human-computer interaction (HCI), there remains a lack of systematic empirical analysis of their real-world application patterns, methodological rigor, and ethical implications in top-tier HCI research. Method: We conducted a systematic literature review and qualitative coding analysis of 153 LLM-related papers published at CHI 2020–2024. Contribution/Results: We propose a novel four-dimensional classification framework—spanning application domains, LLM roles, contribution types, and risks/limitations—and identify five distinct LLM roles in HCI research (e.g., research tool, simulated user). Key findings include overwhelming reliance on closed-source models (92%), widespread concerns regarding validity and reproducibility (>70% of papers explicitly note such issues), and salient ethical risks. This study is the first to empirically trace the evolution of LLM use in CHI. It yields two practical outputs: an HCI+LLM research self-assessment checklist and twelve methodological guiding questions to support rigorous, responsible LLM integration in HCI research.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Humans and AI: Human-Computer Interaction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Large Language Models
• Human-Computer Interaction
• Application Challenges

Innovation

• Large Language Models
• Human-Computer Interaction
• Systematic Review