MétaCan
Menu
← Back to cohort

The Evolving Role of Large Language Models in UX Design: A Bibliometric Analysis Study

2025· article· W4417169780 on OpenAlexaboutno aff
Ilhame Oudor, Khalid Nafil

Bibliographic record

Venuenot available
Typearticle
Language
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsnot available
Fundersnot available
KeywordsField (mathematics)BibliometricsCitationFocus (optics)Systematic reviewOpen researchCitation analysis

Abstract

fetched live from OpenAlex

Context: The advent of large language models (LLMs) have changed the way artificial intelligence interacts with users by understanding and generating natural language. In the field of user experience (UX) design, they open up new ways to improve design processes, support user-centered approaches, and create more inclusive and personalized digital experiences. However, there is still limited research that looks closely at how LLMs are used in UX design. Objective: The primary role of this study is to explore how academic research is addressing the integration of large language models to UX Design. It focuses on identifying current themes, how researchers are working together, and how the focus of the studies has changed over time. Method: This bibliometrics study is based on 42 research papers published between 2022 and 2025, selected from the databases: SpringerLink, IEEE Xplore, ScienceDirect, ACM Digital Library, Scopus, Web of Science, Arxiv, and Dimensions by using the PRISMA method. Tools like Bibliometrix and RStudio were used to analyze publication trends, citation patterns, and the main topics covered in the literature. Results: The findings show that research on LLMs and UX has grown quickly in recent years, especially after the release of tools like ChatGPT. Most of the publications originate from researchers in the USA, China, and Canada. The most common topics include chatbots, co-creation with AI, personalization, and accessibility issues such as fairness and transparency. A few papers were cited often, but many received limited attention, showing that the field is still developing. Conclusion: This analysis synthesizes early research trends in LLM-driven UX design, revealing growing academic interest. Findings highlight the need for deeper investigation into how these models enable inclusive and user-centered solutions, while underscoring the value of cross-disciplinary collaboration between AI and UX fields to advance design innovation.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.050
metaresearch head score (Gemma)0.252
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesBibliometrics
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.899
Threshold uncertainty score0.263

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0500.252
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.1010.198
Science and technology studies0.0030.003
Scholarly communication0.0170.019
Open science0.0010.006
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.133
GPT teacher head0.466
Teacher spread0.333 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicArtificial Intelligence in Healthcare and Education→French-language works237,207→