Designing Trustworthy LLM-based Wellbeing Recommendation through Controllable Interaction

Alan Said; Alexandra Weilenmann

arxiv: 2606.25809 · v1 · pith:ZRWSEWNXnew · submitted 2026-06-24 · 💻 cs.HC

Designing Trustworthy LLM-based Wellbeing Recommendation through Controllable Interaction

Alan Said , Alexandra Weilenmann This is my paper

Pith reviewed 2026-06-25 19:02 UTC · model grok-4.3

classification 💻 cs.HC

keywords LLMwellbeing recommendationcontrollable interactiontrust calibrationintent alignmentrecommender systemshuman-computer interactionexplanation styles

0 comments

The pith

Explicit interaction constraints enable trustworthy LLM-based wellbeing recommendations by structuring conversational behavior.

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

Large language models generate fluent wellbeing advice on topics like physical activity and mental health but rely on implicit prompting that limits oversight of how recommendations are framed and adapted. The paper proposes shifting to a system-level approach that imposes explicit constraints on guidance strategies, explanation styles, degrees of directness, and user control mechanisms. This framework targets three specific problems: calibrating user trust, aligning system intent with user goals, and increasing awareness of recommendation consequences. A sympathetic reader would care because these systems influence real-world actions with long-term health effects. The contribution includes outlining a modular architecture that can be configured and evaluated against outcomes such as self-efficacy and perceived agency.

Core claim

We propose a system-level perspective in which conversational behavior is structured through explicit interaction constraints, including guidance strategies, explanation styles, degrees of directness, and mechanisms for user control. Building on prior work on tangible recommendations, we show how these constraints address key challenges in wellbeing-oriented recommendation, namely trust calibration, intent alignment, and consequence awareness. We outline a modular architecture for controllable LLM-based recommendation and discuss how different configurations can be systematically designed and evaluated in relation to user-centered outcomes such as self-efficacy, perceived agency, and appropr

What carries the argument

The modular architecture for controllable LLM-based recommendation, which structures conversational behavior through explicit interaction constraints to maintain adaptability alongside transparency and user control.

If this is right

Different constraint configurations can be systematically designed and evaluated against outcomes such as self-efficacy, perceived agency, and appropriate reliance.
The approach directly targets trust calibration, intent alignment, and consequence awareness in wellbeing contexts.
The framework enables better responsibility framing and user influence over recommendations that affect long-term outcomes.
It provides a way to retain adaptability while adding transparency and controllability to LLM-based systems.

Where Pith is reading between the lines

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

The same constraint-based structure might apply to other high-stakes recommendation areas such as financial or educational guidance.
Real-world deployment in mobile apps could test whether the constraints improve measurable behavior change over time.
The framework could support development of evaluation benchmarks focused on user agency rather than only recommendation accuracy.

Load-bearing premise

Structuring conversational behavior through explicit interaction constraints will address key challenges in wellbeing-oriented recommendation, namely trust calibration, intent alignment, and consequence awareness.

What would settle it

A user study comparing LLM recommenders with and without the proposed explicit constraints that finds no measurable difference in trust calibration, intent alignment, or consequence awareness.

read the original abstract

Large language models (LLMs) are increasingly used to generate personalized guidance in wellbeing contexts such as physical activity, stress management, and mental health support, enabling fluent and context-aware interaction but relying on largely implicit mechanisms that shape how recommendations are expressed and adapted. We argue that this reliance on implicit adaptation through prompting and alignment limits control over guidance, responsibility framing, and user influence, which is particularly problematic in wellbeing settings where recommendations affect users' actions and long-term outcomes. We propose a system-level perspective in which conversational behavior is structured through explicit interaction constraints, including guidance strategies, explanation styles, degrees of directness, and mechanisms for user control. Building on prior work on tangible recommendations, we show how these constraints address key challenges in wellbeing-oriented recommendation, namely trust calibration, intent alignment, and consequence awareness. We outline a modular architecture for controllable LLM-based recommendation and discuss how different configurations can be systematically designed and evaluated in relation to user-centered outcomes such as self-efficacy, perceived agency, and appropriate reliance. This paper contributes a system-level framework for designing LLM-based recommender systems that are adaptive while remaining transparent, controllable, and aligned with human wellbeing.

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

A clear but untested framework proposal for explicit control in LLM wellbeing recommendations.

read the letter

The paper's core contribution is a system-level framework that structures LLM conversational behavior in wellbeing domains through explicit constraints like guidance strategies, explanation styles, directness levels, and user control mechanisms. It extends prior HCI work on tangible and controllable recommendations to address trust calibration, intent alignment, and consequence awareness in areas such as physical activity and mental health support.

It does a decent job mapping out why implicit prompting falls short in high-stakes wellbeing settings and sketching a modular architecture that could allow systematic design choices. The tie-in to user outcomes like self-efficacy and perceived agency gives the proposal some grounding in existing evaluation practices.

The main limitation is the complete absence of any implementation, prototype, or empirical check. The claims that these constraints will solve the identified problems remain assertions without data or even worked examples to show feasibility. No derivations or tests back up the architecture's effectiveness.

This is aimed at HCI researchers and applied AI designers working on health-related recommenders who want a structured way to think about controllability. It could be useful as a starting point for building and testing systems.

I'd send it for peer review. Frameworks like this can get useful feedback on the design space even if they need substantial follow-up to demonstrate impact.

Referee Report

0 major / 2 minor

Summary. The paper proposes a system-level framework for LLM-based wellbeing recommendation systems (e.g., physical activity, stress management) that structures conversational behavior via explicit interaction constraints—guidance strategies, explanation styles, degrees of directness, and user control mechanisms—rather than relying on implicit prompting and alignment. Building on prior work on tangible recommendations, it outlines a modular architecture for controllable LLM-based recommendation and discusses systematic design and evaluation against user-centered outcomes such as self-efficacy, perceived agency, and appropriate reliance. The central contribution is positioned as a design framework that makes systems adaptive while remaining transparent, controllable, and aligned with human wellbeing, addressing trust calibration, intent alignment, and consequence awareness.

Significance. If the framework is adopted, it supplies a structured design space and research agenda for making LLM recommendations in wellbeing contexts more controllable and transparent. The explicit separation of constraints from core model behavior, the modular architecture, and the mapping to future user-centered evaluation metrics constitute a clear contribution as a conceptual tool rather than an empirical result. This is particularly relevant for sensitive domains where implicit adaptation raises responsibility and alignment issues.

minor comments (2)

[Abstract / framework outline] The abstract and framework description assert that the listed constraints address trust calibration, intent alignment, and consequence awareness, but the text would benefit from one or two concrete configuration examples showing how a specific choice (e.g., a directness degree combined with an explanation style) is intended to affect one of those three outcomes.
[Architecture section] The modular architecture is introduced at a high level; adding a diagram or table that enumerates the modules, their inputs/outputs, and how constraints are enforced would improve clarity for readers wishing to implement or extend the approach.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of our work and the recommendation for minor revision. The summary accurately captures the core contribution of the system-level framework using explicit interaction constraints for LLM-based wellbeing recommenders.

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper is a high-level conceptual proposal for a system-level framework using explicit interaction constraints (guidance strategies, explanation styles, directness, user control) to address trust, alignment, and awareness in LLM wellbeing recommendations. It contains no equations, fitted parameters, predictions, or derivations. The central contribution is the articulation of the architecture and design space, positioned as a direction for future evaluation rather than an asserted result derived from prior inputs. No self-citation forms a load-bearing chain, and the argument does not reduce any claim to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The paper is a conceptual proposal relying on domain assumptions about LLM limitations and the benefits of explicit controls, with no quantitative models, free parameters, or external evidence for invented constructs.

axioms (2)

domain assumption LLMs rely on largely implicit mechanisms that shape how recommendations are expressed and adapted
Stated directly in the abstract as the core problem motivating the work.
ad hoc to paper Explicit interaction constraints address trust calibration, intent alignment, and consequence awareness in wellbeing settings
Central premise of the proposal; no supporting evidence or derivation is provided.

invented entities (1)

modular architecture for controllable LLM-based recommendation no independent evidence
purpose: To structure conversational behavior through explicit constraints on guidance, explanations, directness, and user control
Introduced as the proposed solution; no independent evidence or falsifiable predictions outside the paper are given.

pith-pipeline@v0.9.1-grok · 5726 in / 1556 out tokens · 44211 ms · 2026-06-25T19:02:42.914869+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

21 extracted references · 19 canonical work pages

[1]

Said, Early Explorations of Recommender Systems for Physical Activity and Well-Being, in: L

A. Said, Early Explorations of Recommender Systems for Physical Activity and Well-Being, in: L. Boratto, A. De Filippo, E. Lex, N. Mauro, F. M. Malloci, F. Ricci (Eds.), Recommender Systems for Sustainability and Social Good, Springer Nature Switzerland, Cham, 2026, pp. 117–125. doi:10.1007/978-3-032-13342-7_11

work page doi:10.1007/978-3-032-13342-7_11 2026
[2]

Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz

S. Amershi, D. Weld, M. Vorvoreanu, A. Fourney, B. Nushi, P. Collisson, J. Suh, S. Iqbal, P. N. Bennett, K. Inkpen, J. Teevan, R. Kikin-Gil, E. Horvitz, Guidelines for Human-AI Interaction, in: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI ’19, Association for Computing Machinery, New York, NY, USA, 2019, pp. 1–13. URL:...

work page doi:10.1145/3290605.3300233 2019
[3]

Weidinger, J

L. Weidinger, J. Uesato, M. Rauh, C. Griffin, P.-S. Huang, J. Mellor, A. Glaese, M. Cheng, B. Balle, A. Kasirzadeh, C. Biles, S. Brown, Z. Kenton, W. Hawkins, T. Stepleton, A. Birhane, L. A. Hendricks, L. Rimell, W. Isaac, J. Haas, S. Legassick, G. Irving, I. Gabriel, Taxonomy of Risks posed by Language Models, in: Proceedings of the 2022 ACM Conference o...

work page doi:10.1145/3531146.3533088 2022
[4]

J. D. Lee, K. A. See, Trust in Automation: Designing for Appropriate Reliance, Human Factors 46 (2004) 50–80. URL: https://journals.sagepub.com/action/showAbstract. doi:10.1518/hfes.46.1. 50_30392

work page doi:10.1518/hfes.46.1 2004
[5]

Shneiderman, Human-Centered Artificial Intelligence: Reliable, Safe & Trustwor- thy, International Journal of Human–Computer Interaction 36 (2020) 495–504

B. Shneiderman, Human-Centered Artificial Intelligence: Reliable, Safe & Trustwor- thy, International Journal of Human–Computer Interaction 36 (2020) 495–504. URL: https: //doi.org/10.1080/10447318.2020.1741118. doi: 10.1080/10447318.2020.1741118, _eprint: https://doi.org/10.1080/10447318.2020.1741118

work page doi:10.1080/10447318.2020.1741118 2020
[6]

Appropriate reliance on AI advice: conceptualization and the effect of explanations

M. Schemmer, N. Kuehl, C. Benz, A. Bartos, G. Satzger, Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations, in: Proceedings of the 28th International Conference on Intelligent User Interfaces, IUI ’23, Association for Computing Machinery, New York, NY, USA, 2023, pp. 410–422. URL: https://dl.acm.org/doi/10.1145/3581641.3584...

work page doi:10.1145/3581641.3584066 2023
[7]

Said, On explaining recommendations with Large Language Models: a review, Frontiers in Big Data 7 (2025)

A. Said, On explaining recommendations with Large Language Models: a review, Frontiers in Big Data 7 (2025). URL: https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024. 1505284/full. doi:10.3389/fdata.2024.1505284

work page doi:10.3389/fdata.2024 2025
[8]

Elsweiler, B

D. Elsweiler, B. Ludwig, A. Said, H. Schäfer, C. Trattner, Engendering health with recommender systems: Workshop abstract, in: RecSys 2016 - Proceedings of the 10th ACM Conference on Recommender Systems, 2016. doi:10.1145/2959100.2959203

work page doi:10.1145/2959100.2959203 2016
[9]

Hauptmann, A

H. Hauptmann, A. Said, C. Trattner, Research directions in recommender systems for health and well-being, User Modeling and User-Adapted Interaction 32 (2022) 781–786. URL: https: //doi.org/10.1007/s11257-022-09349-4. doi:10.1007/s11257-022-09349-4

work page doi:10.1007/s11257-022-09349-4 2022
[10]

Schäfer, S

H. Schäfer, S. Hors-Fraile, R. P. Karumur, A. Calero Valdez, A. Said, H. Torkamaan, T. Ulmer, C. Trattner, Towards Health (Aware) Recommender Systems, in: Proceedings of the 2017 International Conference on Digital Health, DH ’17, Association for Computing Machinery, New York, NY, USA, 2017, pp. 157–161. URL: https://dl.acm.org/doi/10.1145/3079452.3079499...

work page doi:10.1145/3079452.3079499 2017
[11]

R. D. Croon, L. V. Houdt, N. N. Htun, G. Štiglic, V. V. Abeele, K. Verbert, Health Recom- mender Systems: Systematic Review, Journal of Medical Internet Research 23 (2021) e18035. URL: https://www.jmir.org/2021/6/e18035. doi:10.2196/18035, company: Journal of Medical Internet Research Distributor: Journal of Medical Internet Research Institution: Journal ...

work page doi:10.2196/18035 2021
[12]

D. Roy, M. Dutta, A systematic review and research perspective on recommender systems, Journal of Big Data 9 (2022) 59. URL: https://doi.org/10.1186/s40537-022-00592-5. doi: 10.1186/ s40537-022-00592-5

work page doi:10.1186/s40537-022-00592-5 2022
[13]

Jannach, A

D. Jannach, A. Said, M. Tkalcic, M. Zanker, Recommender Systems for Good (RS4Good): Survey of Use Cases and a Call to Action for Research that Matters, ACM Trans. Recomm. Syst. (2025). URL: https://dl.acm.org/doi/10.1145/3746648. doi:10.1145/3746648, just Accepted

work page doi:10.1145/3746648 2025
[14]

A. Said, Recommender Systems for Social Good:The Role of Accountability and Sustainability, volume Proceeding of the 2024 workshop on Recommender Systems for Social Good ofRecSoGood, Springer, 2024

2024
[15]

What to compare? towards un- derstanding user sessions on price comparison platforms

V. Kecki, A. Said, Understanding Fairness in Recommender Systems: A Healthcare Perspective, in: Proceedings of the 18th ACM Conference on Recommender Systems, RecSys ’24, Association for Computing Machinery, New York, NY, USA, 2024, pp. 1125–1130. URL: https://dl.acm.org/doi/10. 1145/3640457.3691711. doi:10.1145/3640457.3691711

work page doi:10.1145/3640457.3691711 2024
[16]

Weilenmann, T

A. Weilenmann, T. Hillman, Selfies in the wild: Studying selfie photography as a local practice, Mobile Media & Communication 8 (2020) 42–61. URL: https://doi.org/10.1177/2050157918822131. doi:10.1177/2050157918822131

work page doi:10.1177/2050157918822131 2020
[17]

Cerna, J

K. Cerna, J. Ivarsson, A. Weilenmann, G. Steineck, Supporting self-management of radiation- induced bowel and bladder dysfunction in pelvic-cancer rehabilitation: An ethnographic study, Journal of Clinical Nursing 28 (2019) 2624–2634. doi:10.1111/jocn.14849

work page doi:10.1111/jocn.14849 2019
[18]

Silva, L

I. Silva, L. B. Marinho, A. Said, M. Willemsen, Leveraging ChatGPT for Automated Human- centered Explanations in Recommender Systems, in: Proceedings of the 29th ACM Conference on Intelligent User Interfaces., IUI ’24, ACM, New York, NY, USA, 2024

2024
[19]

X. Sun, Y. Liu, J. De Wit, J. A. Bosch, Z. Li, Trust by Interface: How Different User Interfaces Shape Human Trust in Health Information from Large Language Models, in: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, CHI EA ’24, Association for Computing Machinery, New York, NY, USA, 2024, pp. 1–7. URL: https://dl.acm.org/d...

work page doi:10.1145/3613905.3650837 2024
[20]

J. Chen, Z. Liu, X. Huang, C. Wu, Q. Liu, G. Jiang, Y. Pu, Y. Lei, X. Chen, X. Wang, K. Zheng, D. Lian, E. Chen, When large language models meet personalization: perspectives of challenges and opportunities, World Wide Web 27 (2024) 42. URL: https://doi.org/10.1007/s11280-024-01276-1. doi:10.1007/s11280-024-01276-1

work page doi:10.1007/s11280-024-01276-1 2024
[21]

C. C. Yang, Explainable Artificial Intelligence for Predictive Modeling in Healthcare, Journal of Healthcare Informatics Research 6 (2022) 228–239. URL: https://doi.org/10.1007/ s41666-022-00114-1. doi:10.1007/s41666-022-00114-1

work page doi:10.1007/s41666-022-00114-1 2022

[1] [1]

Said, Early Explorations of Recommender Systems for Physical Activity and Well-Being, in: L

A. Said, Early Explorations of Recommender Systems for Physical Activity and Well-Being, in: L. Boratto, A. De Filippo, E. Lex, N. Mauro, F. M. Malloci, F. Ricci (Eds.), Recommender Systems for Sustainability and Social Good, Springer Nature Switzerland, Cham, 2026, pp. 117–125. doi:10.1007/978-3-032-13342-7_11

work page doi:10.1007/978-3-032-13342-7_11 2026

[2] [2]

Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz

S. Amershi, D. Weld, M. Vorvoreanu, A. Fourney, B. Nushi, P. Collisson, J. Suh, S. Iqbal, P. N. Bennett, K. Inkpen, J. Teevan, R. Kikin-Gil, E. Horvitz, Guidelines for Human-AI Interaction, in: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI ’19, Association for Computing Machinery, New York, NY, USA, 2019, pp. 1–13. URL:...

work page doi:10.1145/3290605.3300233 2019

[3] [3]

Weidinger, J

L. Weidinger, J. Uesato, M. Rauh, C. Griffin, P.-S. Huang, J. Mellor, A. Glaese, M. Cheng, B. Balle, A. Kasirzadeh, C. Biles, S. Brown, Z. Kenton, W. Hawkins, T. Stepleton, A. Birhane, L. A. Hendricks, L. Rimell, W. Isaac, J. Haas, S. Legassick, G. Irving, I. Gabriel, Taxonomy of Risks posed by Language Models, in: Proceedings of the 2022 ACM Conference o...

work page doi:10.1145/3531146.3533088 2022

[4] [4]

J. D. Lee, K. A. See, Trust in Automation: Designing for Appropriate Reliance, Human Factors 46 (2004) 50–80. URL: https://journals.sagepub.com/action/showAbstract. doi:10.1518/hfes.46.1. 50_30392

work page doi:10.1518/hfes.46.1 2004

[5] [5]

Shneiderman, Human-Centered Artificial Intelligence: Reliable, Safe & Trustwor- thy, International Journal of Human–Computer Interaction 36 (2020) 495–504

B. Shneiderman, Human-Centered Artificial Intelligence: Reliable, Safe & Trustwor- thy, International Journal of Human–Computer Interaction 36 (2020) 495–504. URL: https: //doi.org/10.1080/10447318.2020.1741118. doi: 10.1080/10447318.2020.1741118, _eprint: https://doi.org/10.1080/10447318.2020.1741118

work page doi:10.1080/10447318.2020.1741118 2020

[6] [6]

Appropriate reliance on AI advice: conceptualization and the effect of explanations

M. Schemmer, N. Kuehl, C. Benz, A. Bartos, G. Satzger, Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations, in: Proceedings of the 28th International Conference on Intelligent User Interfaces, IUI ’23, Association for Computing Machinery, New York, NY, USA, 2023, pp. 410–422. URL: https://dl.acm.org/doi/10.1145/3581641.3584...

work page doi:10.1145/3581641.3584066 2023

[7] [7]

Said, On explaining recommendations with Large Language Models: a review, Frontiers in Big Data 7 (2025)

A. Said, On explaining recommendations with Large Language Models: a review, Frontiers in Big Data 7 (2025). URL: https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024. 1505284/full. doi:10.3389/fdata.2024.1505284

work page doi:10.3389/fdata.2024 2025

[8] [8]

Elsweiler, B

D. Elsweiler, B. Ludwig, A. Said, H. Schäfer, C. Trattner, Engendering health with recommender systems: Workshop abstract, in: RecSys 2016 - Proceedings of the 10th ACM Conference on Recommender Systems, 2016. doi:10.1145/2959100.2959203

work page doi:10.1145/2959100.2959203 2016

[9] [9]

Hauptmann, A

H. Hauptmann, A. Said, C. Trattner, Research directions in recommender systems for health and well-being, User Modeling and User-Adapted Interaction 32 (2022) 781–786. URL: https: //doi.org/10.1007/s11257-022-09349-4. doi:10.1007/s11257-022-09349-4

work page doi:10.1007/s11257-022-09349-4 2022

[10] [10]

Schäfer, S

H. Schäfer, S. Hors-Fraile, R. P. Karumur, A. Calero Valdez, A. Said, H. Torkamaan, T. Ulmer, C. Trattner, Towards Health (Aware) Recommender Systems, in: Proceedings of the 2017 International Conference on Digital Health, DH ’17, Association for Computing Machinery, New York, NY, USA, 2017, pp. 157–161. URL: https://dl.acm.org/doi/10.1145/3079452.3079499...

work page doi:10.1145/3079452.3079499 2017

[11] [11]

R. D. Croon, L. V. Houdt, N. N. Htun, G. Štiglic, V. V. Abeele, K. Verbert, Health Recom- mender Systems: Systematic Review, Journal of Medical Internet Research 23 (2021) e18035. URL: https://www.jmir.org/2021/6/e18035. doi:10.2196/18035, company: Journal of Medical Internet Research Distributor: Journal of Medical Internet Research Institution: Journal ...

work page doi:10.2196/18035 2021

[12] [12]

D. Roy, M. Dutta, A systematic review and research perspective on recommender systems, Journal of Big Data 9 (2022) 59. URL: https://doi.org/10.1186/s40537-022-00592-5. doi: 10.1186/ s40537-022-00592-5

work page doi:10.1186/s40537-022-00592-5 2022

[13] [13]

Jannach, A

D. Jannach, A. Said, M. Tkalcic, M. Zanker, Recommender Systems for Good (RS4Good): Survey of Use Cases and a Call to Action for Research that Matters, ACM Trans. Recomm. Syst. (2025). URL: https://dl.acm.org/doi/10.1145/3746648. doi:10.1145/3746648, just Accepted

work page doi:10.1145/3746648 2025

[14] [14]

A. Said, Recommender Systems for Social Good:The Role of Accountability and Sustainability, volume Proceeding of the 2024 workshop on Recommender Systems for Social Good ofRecSoGood, Springer, 2024

2024

[15] [15]

What to compare? towards un- derstanding user sessions on price comparison platforms

V. Kecki, A. Said, Understanding Fairness in Recommender Systems: A Healthcare Perspective, in: Proceedings of the 18th ACM Conference on Recommender Systems, RecSys ’24, Association for Computing Machinery, New York, NY, USA, 2024, pp. 1125–1130. URL: https://dl.acm.org/doi/10. 1145/3640457.3691711. doi:10.1145/3640457.3691711

work page doi:10.1145/3640457.3691711 2024

[16] [16]

Weilenmann, T

A. Weilenmann, T. Hillman, Selfies in the wild: Studying selfie photography as a local practice, Mobile Media & Communication 8 (2020) 42–61. URL: https://doi.org/10.1177/2050157918822131. doi:10.1177/2050157918822131

work page doi:10.1177/2050157918822131 2020

[17] [17]

Cerna, J

K. Cerna, J. Ivarsson, A. Weilenmann, G. Steineck, Supporting self-management of radiation- induced bowel and bladder dysfunction in pelvic-cancer rehabilitation: An ethnographic study, Journal of Clinical Nursing 28 (2019) 2624–2634. doi:10.1111/jocn.14849

work page doi:10.1111/jocn.14849 2019

[18] [18]

Silva, L

I. Silva, L. B. Marinho, A. Said, M. Willemsen, Leveraging ChatGPT for Automated Human- centered Explanations in Recommender Systems, in: Proceedings of the 29th ACM Conference on Intelligent User Interfaces., IUI ’24, ACM, New York, NY, USA, 2024

2024

[19] [19]

X. Sun, Y. Liu, J. De Wit, J. A. Bosch, Z. Li, Trust by Interface: How Different User Interfaces Shape Human Trust in Health Information from Large Language Models, in: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, CHI EA ’24, Association for Computing Machinery, New York, NY, USA, 2024, pp. 1–7. URL: https://dl.acm.org/d...

work page doi:10.1145/3613905.3650837 2024

[20] [20]

J. Chen, Z. Liu, X. Huang, C. Wu, Q. Liu, G. Jiang, Y. Pu, Y. Lei, X. Chen, X. Wang, K. Zheng, D. Lian, E. Chen, When large language models meet personalization: perspectives of challenges and opportunities, World Wide Web 27 (2024) 42. URL: https://doi.org/10.1007/s11280-024-01276-1. doi:10.1007/s11280-024-01276-1

work page doi:10.1007/s11280-024-01276-1 2024

[21] [21]

C. C. Yang, Explainable Artificial Intelligence for Predictive Modeling in Healthcare, Journal of Healthcare Informatics Research 6 (2022) 228–239. URL: https://doi.org/10.1007/ s41666-022-00114-1. doi:10.1007/s41666-022-00114-1

work page doi:10.1007/s41666-022-00114-1 2022