arxiv: 2604.04353 · v2 · submitted 2026-04-06 · 💻 cs.HC · cs.AI

Recognition: no theorem link

ReFinE: Streamlining UI Mockup Iteration with Research Findings

Donghoon Shin , Bingcan Guo , Jaewook Lee , Lucy Lu Wang , Gary Hsieh

Authors on Pith no claims yet

Pith reviewed 2026-05-10 20:19 UTC · model grok-4.3

classification 💻 cs.HC cs.AI

keywords HCI researchUI mockupsFigma plugindesign implicationsresearch to practicecontextual insightsiterative design

0 comments

The pith

ReFinE is a Figma plugin that identifies relevant HCI research and provides tailored visual suggestions for updating UI mockups.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents ReFinE as a way to help designers bring findings from HCI studies into their actual design work inside Figma. Many designers have trouble locating papers, understanding their language, and figuring out concrete steps to take from them. ReFinE solves this by analyzing the mockup in real time, pulling matching insights, condensing them into specific design changes, and showing those changes as visual overlays. A technical evaluation and user study indicate that the tool lowers the mental effort needed and makes it easier to use evidence in designs. If successful, this kind of tool could make research more usable in everyday practice.

Core claim

ReFinE identifies and synthesizes design implications from HCI literature relevant to the mockup's design context, and tailors this research evidence to a specific design mockup by providing actionable visual guidance on how to update the mockup.

What carries the argument

The ReFinE Figma plugin mechanism that analyzes mockup context to retrieve, synthesize, and visualize research-based design recommendations.

If this is right

Designers spend less time searching for and interpreting research papers during mockup creation.
Research findings translate more directly into design changes through visual guidance rather than abstract text.
UI mockups can incorporate evidence-based improvements more consistently across iterations.
Designers report lower cognitive load when applying scholarly insights to their work.
Broader adoption could reduce the divide between academic HCI results and professional design outcomes.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Similar real-time research integration tools could be developed for other creative software beyond Figma.
Researchers might start structuring papers with more explicit design implications to improve compatibility with such systems.
Long-term use could lead to designs that better reflect accumulated HCI knowledge, potentially improving end-user experiences.
Further studies in real-world design teams would test whether the benefits hold when mockups are more complex or teams are larger.

Load-bearing premise

The plugin can reliably find relevant papers and generate accurate, context-appropriate guidance without errors from incomplete literature coverage or misread design elements.

What would settle it

A controlled comparison where mockups revised with ReFinE guidance are reviewed by experts for alignment with the cited research, and any systematic mismatches would disprove the effectiveness claim.

Figures

Figures reproduced from arXiv: 2604.04353 by Bingcan Guo, Donghoon Shin, Gary Hsieh, Jaewook Lee, Lucy Lu Wang.

**Figure 1.** Figure 1: An overview of the ReFinE-aided design workflow. Based on a user’s selected UI mockup on the Figma canvas, the system generates ○1 clusters of research insight informed by HCI research papers. Designers can examine ○2 each cluster to understand the synthesized design implications before reviewing ○3 action items and their visualizations, which project how potential design edits could be made to the interfa… view at source ↗

**Figure 2.** Figure 2: Pipeline for generating the components provided by [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗

**Figure 3.** Figure 3: Contents of the cluster and their formulation [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗

**Figure 4.** Figure 4: An example of mockup reconstruction in our [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗

**Figure 6.** Figure 6: Design outputs from iterating two example mockups with [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗

**Figure 7.** Figure 7: Perceived workload, communication quality, and the design output metrics from our user study. Participants in the [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗

**Figure 8.** Figure 8: P4’s example of implementing an action item. After [PITH_FULL_IMAGE:figures/full_fig_p011_8.png] view at source ↗

**Figure 9.** Figure 9: Prototype mockups used in our user study [PITH_FULL_IMAGE:figures/full_fig_p017_9.png] view at source ↗

read the original abstract

Although HCI research papers offer valuable design insights, designers often struggle to apply them in design workflows due to difficulties in finding relevant literature, understanding technical jargon, the lack of contextualization, and limited actionability. To address these challenges, we present ReFinE, a Figma plugin that supports real-time design iteration by surfacing contextualized insights from research papers. ReFinE identifies and synthesizes design implications from HCI literature relevant to the mockup's design context, and tailors this research evidence to a specific design mockup by providing actionable visual guidance on how to update the mockup. To assess the system's effectiveness, we conducted a technical evaluation and a user study. Results show that ReFinE effectively synthesizes and contextualizes design implications, reducing cognitive load and improving designers' ability to integrate research evidence into UI mockups. This work contributes to bridging the gap between research and design practice by presenting a tool for embedding scholarly insights into the UI design process.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

ReFinE is a Figma plugin that pulls HCI papers, synthesizes implications, and gives visual update suggestions on mockups, but the abstract leaves the supporting studies almost completely undescribed.

read the letter

ReFinE is a Figma plugin that scans a UI mockup, finds relevant HCI papers, pulls out design implications, and then shows visual guidance on how to revise the mockup based on that research. The real-time synthesis plus direct visual overlay is the part that feels new compared to earlier literature search tools or static summaries. It targets a practical pain point: designers who want research input but hit jargon, lack of context, and no clear next steps. If the system actually delivers accurate, tailored suggestions without much extra effort, it could make research uptake a bit easier in everyday design work. The abstract claims the technical evaluation and user study back this up, with lower cognitive load and better integration of evidence. That direction makes sense for an HCI systems paper. The soft spot is the complete absence of study details. No sample size, no tasks, no metrics, no baselines, and no numbers on how well the synthesis actually worked or how often it produced errors. Without those, the effectiveness claim stays untested on the page. The reliability of the paper-identification and synthesis steps also gets little attention, which matters because bad recommendations would undermine the whole point. This is for HCI researchers and tool builders focused on research-practice gaps or design-support systems. A reader who cares about closing that gap would find the workflow worth seeing. It deserves a serious referee because the core idea is grounded in a real workflow problem and the contribution is a concrete implementation rather than another survey. Send it to review, but ask the authors to expand the evaluation section with full methods, quantitative results, and any limitations on synthesis accuracy.

Referee Report

2 major / 2 minor

Summary. The paper presents ReFinE, a Figma plugin that identifies relevant HCI research papers for a given UI mockup, synthesizes design implications from the literature, contextualizes them to the specific design context, and generates actionable visual guidance for updating the mockup. The authors report results from a technical evaluation and a user study showing that the system effectively reduces cognitive load and improves designers' ability to integrate research evidence into their workflows.

Significance. If the empirical claims hold under scrutiny, this work could meaningfully advance the translation of HCI research into practice by embedding automated literature synthesis and contextualization directly into a widely used design tool. It addresses documented barriers such as literature discovery, jargon, and actionability, and offers a concrete system contribution that could increase the uptake of research findings in industry design processes.

major comments (2)

[User Study] User Study section: the manuscript provides no details on participant count, recruitment method, task design, quantitative metrics for cognitive load or integration improvement, control conditions, or statistical analysis. These elements are load-bearing for the central effectiveness claim and must be reported with sufficient rigor to allow replication and assessment of validity.
[Technical Evaluation] Technical Evaluation section: the description of how relevance identification, synthesis accuracy, contextualization quality, and guidance actionability were measured is absent or insufficient, including any baselines, error rates, or quantitative results. Without these specifics, the assertion that ReFinE 'effectively synthesizes and contextualizes design implications' cannot be evaluated.

minor comments (2)

[Abstract] Abstract: expand the results sentence to include at least one concrete outcome metric or qualitative finding rather than the current high-level summary.
[Throughout] Notation and terminology: ensure consistent use of terms such as 'design implications,' 'actionable guidance,' and 'contextualization' across sections to avoid ambiguity for readers.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback. The comments highlight important gaps in the reporting of our evaluation methods, and we will revise the manuscript to address them fully.

read point-by-point responses

Referee: [User Study] User Study section: the manuscript provides no details on participant count, recruitment method, task design, quantitative metrics for cognitive load or integration improvement, control conditions, or statistical analysis. These elements are load-bearing for the central effectiveness claim and must be reported with sufficient rigor to allow replication and assessment of validity.

Authors: We agree that the User Study section lacks the required methodological details. This omission prevents proper evaluation of the effectiveness claims. In the revised manuscript we will expand the section to report participant count, recruitment method, task design, quantitative metrics (including those for cognitive load and research integration), control conditions, and statistical analysis, enabling replication and validity assessment. revision: yes
Referee: [Technical Evaluation] Technical Evaluation section: the description of how relevance identification, synthesis accuracy, contextualization quality, and guidance actionability were measured is absent or insufficient, including any baselines, error rates, or quantitative results. Without these specifics, the assertion that ReFinE 'effectively synthesizes and contextualizes design implications' cannot be evaluated.

Authors: We agree that the Technical Evaluation section does not provide sufficient detail on the measurement procedures. We will revise the section to explicitly describe the methods for assessing relevance identification, synthesis accuracy, contextualization quality, and guidance actionability, including baselines, error rates, and quantitative results. This will allow readers to evaluate the supporting evidence for our claims. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper is a descriptive systems contribution that presents a Figma plugin and supports its claims via a technical evaluation plus a user study. No equations, fitted parameters, or derivation chain exist. Central claims about synthesis effectiveness and cognitive-load reduction rest on the reported empirical results rather than any self-referential reduction to inputs or load-bearing self-citations. The work is self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

This is an applied HCI systems paper with no mathematical derivations, fitted parameters, or theoretical axioms; the central contribution is the implemented tool and its reported evaluation.

invented entities (1)

ReFinE Figma plugin no independent evidence
purpose: To surface and contextualize HCI research insights for real-time UI mockup iteration
The plugin itself is the novel artifact introduced by the paper.

pith-pipeline@v0.9.0 · 5474 in / 1204 out tokens · 55376 ms · 2026-05-10T20:19:55.073344+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

55 extracted references · 55 canonical work pages · 2 internal anchors

[2]

2024.Papers

CHI 2024. 2024.Papers. https://chi2024.acm.org/for-authors/papers/

work page 2024
[3]

Robin S Adams. 2002. Understanding Design Iteration: Representations from an Empirical Study. InCommon Ground - DRS International Conference 200. https:// dl.designresearchsociety.org/drs-conference-papers/drs2002/researchpapers/2

work page 2002
[4]

Armen Aghajanyan, Dmytro Okhonko, Mike Lewis, Mandar Joshi, Hu Xu, Gargi Ghosh, and Luke Zettlemoyer. 2021. HTLM: Hyper-Text Pre-Training and Prompting of Language Models.arXiv preprint arXiv:2107.06955(2021). https://arxiv.org/abs/2107.06955

work page arXiv 2021
[5]

2024.Claude 3.5 Sonnet

Anthropic. 2024.Claude 3.5 Sonnet. https://www.anthropic.com/news/claude-3- 5-sonnet

work page 2024
[6]

2018.New Release: arXiv Search v0.1

arXiv. 2018.New Release: arXiv Search v0.1. https://blog.arxiv.org/2018/04/17/ new-release-arxiv-search-v0-1/

work page 2018
[7]

Tal August, Lucy Lu Wang, Jonathan Bragg, Marti A Hearst, Andrew Head, and Kyle Lo. 2023. Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing.ACM Transactions on Computer-Human Interaction30, 5 (2023). doi:10.1145/3589955

work page doi:10.1145/3589955 2023
[8]

Peter Bailis, Simon Peter, and Justine Sherry. 2016. Introducing Research For Practice.Commun. ACM59, 9 (2016). doi:10.1145/2909474

work page doi:10.1145/2909474 2016
[9]

Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psy- chology.Qualitative Research in Psychology3, 2 (2006), 77–101. doi:10.1191/ 1478088706QP063OA

work page 2006
[10]

Sara Bunian, Kai Li, Chaima Jemmali, Casper Harteveld, Yun Fu, and Magy Seif Seif El-Nasr. 2021. VINS: Visual Search for Mobile User Interface Design. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3411764.3445762

work page doi:10.1145/3411764.3445762 2021
[11]

Andrea Burns, Krishna Srinivasan, Joshua Ainslie, Geoff Brown, Bryan A Plum- mer, Kate Saenko, Jianmo Ni, and Mandy Guo. 2023. A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding.arXiv preprint arXiv:2305.03668(2023). https://arxiv.org/abs/2305.03668

work page arXiv 2023
[12]

Joel Chan, Katherine Fu, Christian Schunn, Jonathan Cagan, Kristin Wood, and Kenneth Kotovsky. 2011. On the Benefits and Pitfalls of Analogies for Innovative Design: Ideation Performance Based on Analogical Distance, Commonness, and Modality of Examples.Journal of Mechanical Design133, 8 (08 2011). doi:10.1115/ 1.4004396

work page 2011
[13]

Lucas Colusso, Cynthia L Bennett, Gary Hsieh, and Sean A Munson. 2017. Trans- lational Resources: Reducing the Gap Between Academic Research and HCI Practice. InProceedings of the 2017 Conference on Designing Interactive Systems. doi:10.1145/3064663.3064667

work page doi:10.1145/3064663.3064667 2017
[14]

Lucas Colusso, Ridley Jones, Sean A Munson, and Gary Hsieh. 2019. A Transla- tional Science Model for HCI. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3290605.3300231

work page doi:10.1145/3290605.3300231 2019
[15]

Biplab Deka, Zifeng Huang, Chad Franzen, Joshua Hibschman, Daniel Afergan, Yang Li, Jeffrey Nichols, and Ranjitha Kumar. 2017. Rico: A Mobile App Dataset for Building Data-Driven Design Applications. InProceedings of the 30th Annual ACM Symposium on User Interface Software and Technology. doi:10.1145/3126594. 3126651

work page doi:10.1145/3126594 2017
[16]

Xiang Deng, Prashant Shiralkar, Colin Lockard, Binxuan Huang, and Huan Sun

work page
[17]

arXiv preprint arXiv:2201.10608(2022)

DOM-LM: Learning Generalizable Representations for HTML Documents. arXiv preprint arXiv:2201.10608(2022). https://arxiv.org/abs/2201.10608

work page arXiv 2022
[18]

Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xi- aohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.arXiv preprint arXiv:2010.11929(2020). https://arxiv.org/abs/2010.11929

work page internal anchor Pith review Pith/arXiv arXiv 2020
[19]

Peitong Duan, Jeremy Warner, Yang Li, and Bjoern Hartmann. 2024. Generating Automatic Feedback on UI Mockups with Large Language Models. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. doi:10.1145/ 3613904.3642782

work page arXiv 2024
[20]

Jennifer Ferreira, James Noble, and Robert Biddle. 2007. Agile Development Iterations and UI Design. InAgile 2007. IEEE. doi:10.1109/AGILE.2007.8

work page doi:10.1109/agile.2007.8 2007
[21]

Raymond Fok, Joseph Chee Chang, Tal August, Amy X Zhang, and Daniel S Weld. 2024. Qlarify: Recursively Expandable Abstracts for Dynamic Information Retrieval over Scientific Papers. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. doi:10.1145/3654777.3676397

work page doi:10.1145/3654777.3676397 2024
[22]

Dedre Gentner and Arthur B Markman. 1997. Structure Mapping in Analogy and Similarity.American Psychologist52, 1 (1997). doi:10.1037/0003-066X.52.1.45

work page doi:10.1037/0003-066x.52.1.45 1997
[23]

Karni Gilon, Joel Chan, Felicia Y Ng, Hila Liifshitz-Assaf, Aniket Kittur, and Dafna Shahaf. 2018. Analogy Mining for Specific Design Needs. InProceedings of the 2018 CHI Conference on Human Factors in Computing Systems. doi:10.1145/ 3173574.3173695

work page arXiv 2018
[24]

2024.Embeddings

Google. 2024.Embeddings. https://ai.google.dev/gemini-api/docs/embeddings

work page 2024
[25]

2024.Gemini 2.0 Flash

Google. 2024.Gemini 2.0 Flash. https://ai.google.dev/gemini-api/docs/models/ gemini

work page 2024
[26]

Izzeddin Gur, Hiroki Furuta, Austin Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust. 2023. A Real-World WebAgent with Plan- ning, Long Context Understanding, and Program Synthesis.arXiv preprint arXiv:2307.12856(2023). https://arxiv.org/abs/2307.12856

work page internal anchor Pith review arXiv 2023
[27]

Sandra G Hart and Lowell E Staveland. 1988. Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research. InAdvances in Psychology. Vol. 52. Elsevier. doi:10.1016/S0166-4115(08)62386-9

work page doi:10.1016/s0166-4115(08)62386-9 1988
[28]

Scarlett R Herring, Chia-Chen Chang, Jesse Krantzler, and Brian P Bailey. 2009. Getting Inspired! Understanding How and Why Examples are Used in Creative Design Practice. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. doi:10.1145/1518701.1518717

work page doi:10.1145/1518701.1518717 2009
[29]

Bryan Howell, Asa Jackson, Henry Lee, Julienne DeVita, and Rebekah Rawlings

work page
[30]

InLearn X Design 2021: Engaging with Challenges in Design Education

Exploring the Experiential Reading Differences between Visual and Written Research Papers. InLearn X Design 2021: Engaging with Challenges in Design Education. doi:10.21606/drs_lxd2021.03.247

work page doi:10.21606/drs_lxd2021.03.247 2021
[31]

Yoonjoo Lee, Hyeonsu B Kang, Matt Latzke, Juho Kim, Jonathan Bragg, Joseph Chee Chang, and Pao Siangliulue. 2024. PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Pa- pers. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3613904.3642196

work page doi:10.1145/3613904.3642196 2024
[32]

Luis A Leiva, Asutosh Hota, and Antti Oulasvirta. 2020. Enrico: A Dataset for Topic Modeling of Mobile UI Designs. In22nd International Conference on Human- Computer Interaction with Mobile Devices and Services. doi:10.1145/3406324. 3410710

work page doi:10.1145/3406324 2020
[33]

Junlong Li, Yiheng Xu, Lei Cui, and Furu Wei. 2021. MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding.arXiv preprint arXiv:2110.08518(2021). https://arxiv.org/abs/2110.08518

work page arXiv 2021
[34]

Patrice Lopez. 2009. GROBID: Combining Automatic Bibliographic Data Recog- nition and Term Extraction for Scholarship Publications. InResearch and Ad- vanced Technology for Digital Libraries. Springer Berlin Heidelberg, 473–474. doi:10.1007/978-3-642-04346-8_62

work page doi:10.1007/978-3-642-04346-8_62 2009
[35]

Yuwen Lu, Alan Leung, Amanda Swearngin, Jeffrey Nichols, and Titus Barik. 2025. Misty: UI Prototyping Through Interactive Conceptual Blending. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. doi:10.1145/ 3706598.3713924

work page arXiv 2025
[36]

Jenny Ma, Karthik Sreedhar, Vivian Liu, Sitong Wang, Pedro Alejandro Perez, and Lydia B Chilton. 2024. DIDUP: Dynamic Iterative Development for UI Prototyping. arXiv preprint arXiv:2407.08474(2024). https://arxiv.org/abs/2407.08474

work page arXiv 2024
[37]

Jakob Nielsen. 2002. Iterative User-Interface Design.Computer26, 11 (2002). doi:10.1109/2.241424

work page doi:10.1109/2.241424 2002
[38]

Donald A Norman. 2010. The Research-Practice Gap: The Need for Translational Developers.Interactions17, 4 (2010). doi:10.1145/1806491.1806494

work page doi:10.1145/1806491.1806494 2010
[39]

Novia Nurain, Chia-Fang Chung, Clara Caldeira, and Kay Connelly. 2024. Design- ing a Card-Based Design Tool to Bridge Academic Research & Design Practice For Societal Resilience. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3613904.3642686

work page doi:10.1145/3613904.3642686 2024
[40]

2024.GPT-4o

OpenAI. 2024.GPT-4o. https://openai.com/index/hello-gpt-4o/

work page 2024
[41]

We Are Visual Thinkers, Not Verbal Thinkers!

Hyerim Park, Joscha Eirich, Andre Luckow, and Michael Sedlmair. 2024. "We Are Visual Thinkers, Not Verbal Thinkers!": A Thematic Analysis of How Professional Designers Use Generative AI Image Generation Tools. InProceedings of the 13th Nordic Conference on Human-Computer Interaction. doi:10.1145/3679318.3685370

work page doi:10.1145/3679318.3685370 2024
[42]

Seokhyeon Park, Yumin Song, Soohyun Lee, Jaeyoung Kim, and Jinwook Seo

work page
[43]

In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

Leveraging Multimodal LLM for Inspirational User Interface Search. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3706598.3714213

work page doi:10.1145/3706598.3714213 2025
[44]

Peter J Rousseeuw. 1987. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis.J. Comput. Appl. Math.20 (1987). doi:10.1016/0377- 0427(87)90125-7 ReFinE DIS ’26, June 13–17, 2026, Singapore, Singapore

work page doi:10.1016/0377- 1987
[45]

Corina Sas, Steve Whittaker, Steven Dow, Jodi Forlizzi, and John Zimmerman

work page
[46]

InProceedings of the SIGCHI Conference on Human Factors in Computing Systems

Generating Implications for Design through Design Research. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. doi:10.1145/ 2556288.2557357

work page arXiv
[47]

Donghoon Shin, Tze-Yu Chen, Gary Hsieh, and Lucy Lu Wang. 2025. What About My Design Context?: Exploring the Use of Generative AI to Support Customization of Translational Research Artifacts. InProceedings of the 2025 ACM Designing Interactive Systems Conference. doi:10.1145/3715336.3735686

work page doi:10.1145/3715336.3735686 2025
[48]

Donghoon Shin, Lucy Lu Wang, and Gary Hsieh. 2024. From Paper to Card: Transforming Design Implications with Generative AI. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3613904. 3642266

work page doi:10.1145/3613904 2024
[49]

Sarah Suleri, Nilda Kipi, Linh Chi Tran, and Matthias Jarke. 2019. UI Design Pattern-driven Rapid Prototyping for Agile Development of Mobile Applications. InProceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services. doi:10.1145/3338286.3344399

work page doi:10.1145/3338286.3344399 2019
[50]

Bryan Wang, Gang Li, and Yang Li. 2023. Enabling Conversational Interaction with Mobile UI using Large Language Models. InProceedings of the 2023 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3544548.3580895

work page doi:10.1145/3544548.3580895 2023
[51]

Taylor Webb, Keith J Holyoak, and Hongjing Lu. 2023. Emergent Analogical Reasoning in Large Language Models.Nature Human Behaviour7, 9 (2023). doi:10.1038/s41562-023-01659-w

work page doi:10.1038/s41562-023-01659-w 2023
[52]

Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, F. Xia, Quoc Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Rea- soning in Large Language Models.Advances in Neural Information Processing Systems35 (2022). https://proceedings.neurips.cc/paper_files/paper/2022/file/ 9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf

work page 2022
[53]

Ziming Wu, Qianyao Xu, Yiding Liu, Zhenhui Peng, Yingqing Xu, and Xiaojuan Ma. 2021. Exploring Designers’ Practice of Online Example Management for Supporting Mobile UI Design. InProceedings of the 23rd International Conference on Mobile Human-Computer Interaction. doi:10.1145/3447526.3472048

work page doi:10.1145/3447526.3472048 2021
[54]

Junchi Yu, Ran He, and Zhitao Ying. 2024. Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models. InThe Twelfth International Conference on Learning Representations. doi:10.48550/arXiv.2310. 03965

work page doi:10.48550/arxiv.2310 2024
[55]

Lixiu Yu, Aniket Kittur, and Robert E Kraut. 2014. Searching for Analogical Ideas with Crowds. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems. doi:10.1145/2556288.2557378

work page doi:10.1145/2556288.2557378 2014
[56]

Ruican Zhong, Donghoon Shin, Rosemary Meza, Predrag Klasnja, Lucas Colusso, and Gary Hsieh. 2024. AI-Assisted Causal Pathway Diagram for Human-Centered Design. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. doi:10.1145/3613904.3642179 DIS ’26, June 13–17, 2026, Singapore, Singapore Shin, et al. A Technical Implementation D...

work page doi:10.1145/3613904.3642179 2024