The 1st Workshop
on Trustworthy and Adaptive LLMs for Mental and Physical Wellbeing in Recommendations

Large Language Models (LLMs) are rapidly transforming recommender systems (RSs) and user modeling by enabling richer representations of users, context, and intent. In wellbeing-oriented applications, such as activity, diet, stress, and mental health support, the use of LLM-based RSs introduces both new opportunities and critical challenges related to trustworthiness, adaptivity, explainability, privacy, and human-centered evaluation. This workshop aims to bring together researchers and industry practitioners from user modeling, personalization, RSs and healthcare to examine how LLM-based models can be responsibly designed, evaluated, and deployed for mental and physical wellbeing, fostering AI for social good. Strongly aligned with the UMAP community, this workshop emphasizes adaptive and personalized systems that place human values at the center. Through paper presentations, invited talks, and interactive discussions, this workshop will surface open challenges, emerging best practices, and future research directions for LLM-driven wellbeing recommendation.

Important Dates

• Workshop paper submission: April 9, 2026
• Workshop paper notification: April 28 13, 2026
• Workshop paper camera-ready: May 7, 2026
• Workshops: June 8, 2026

TIMEZONE: Anywhere On Earth (UTC-12)

Workshop Objectives

This workshop aims to provide a focused forum for discussing trustworthy and adaptive LLM-based recommendation for mental and physical wellbeing. The key objectives are to:

1. Explore how LLMs can support adaptive user modeling of dynamic, affective, and longitudinal wellbeing states.
2. Investigate explainable, fair, privacy-preserving, and robust recommendation strategies tailored to wellbeing contexts.
3. Advance evaluation and benchmarking methodologies that reflect real-world human impact, individual outcomes, and long-term adaptation.

Call for Papers

We welcome submissions on the following topics (but not limited to):

• LLM-based User Modeling for Wellbeing: modeling dynamic, affective, and longitudinal user states using LLMs, including representations of mood, stress, activity, and lifestyle factors.
• Adaptive and Personalized Recommendation Strategies: LLM-driven approaches for activity, lifestyle, and wellbeing recommendations that adapt over time and across contexts.
• Trustworthiness in LLM-based Recommendation: explainability, transparency, robustness, calibration, and uncertainty estimation in wellbeing-oriented recommenders.
• Fairness, Bias, and Inclusivity: subgroup performance analysis, cultural and demographic sensitivity, and mitigation of bias in LLM-based personalization.
• Privacy-Preserving and Responsible Personalization: on-device and federated learning, differential privacy, and lightweight or distilled LLMs for sensitive wellbeing data.
• Human-Centered and Human-in-the-Loop Evaluation: evaluation methodologies that capture individual outcomes, long-term effects, and user trust, including interactive and participatory evaluation.
• LLM-based User Simulation and Benchmarking: simulation of user behavior and feedback for scalable evaluation, benchmarking, and stress-testing of wellbeing RSs.
• Deployment and Real-World Challenges: system design, safety boundaries, and deployment of LLM-based recommenders in real-world, resource-constrained, or web-scale wellbeing applications.

For detailed topics and submission guidelines, visit the Call for Papers page.

Submission Guidelines

All submitted papers must be formatted as a single PDF document according to the ACM UMAP 2026 template.

• Length: 4-8 pages (up to 4 additional pages for references and appendix if included in proceedings; unlimited otherwise)
• Review Policy: Single-blind review
• Evaluation Criteria: Relevance to the workshop, scientific novelty, and technical quality

Submission Portal: https://easychair.org/my2/conference?conf=llm4wellrecumap

Program Highlights

This workshop will feature:

• Keynote Talks: Two 30-minute keynote talks delivered by leading researchers and industry experts in LLM4WellRec, providing valuable insights into the latest advancements and future prospects.
• Paper Sessions: Presentations of accepted papers showcasing cutting-edge research.
• Poster and Networking: Present papers through poster sessions and engage in in-depth discussions with researchers and industry practitioners to exchange ideas, receive feedback, and explore potential collaborations.

Organizing Committee

• Zhu Sun, Assistant Professor, Singapore University of Technology and Design
• Yi Ding, Assistant Professor, Purdue University, USA
• Yin Leng Theng, Professor, Nanyang Technological University, Singapore
• Wei Quin Yow, Professor, Singapore University of Technology and Design
• Roy Ka-Wei Lee, Assistant Professor, Singapore University of Technology and Design
• Xun Jiang, CEO, Theta AI, USA