Designing Trustworthy LLM-based Wellbeing Recommendation through Controllable Interaction

2026-06-24

AI Summary

Current large language models (LLMs) rely on implicit mechanisms for mental and physical well-being recommendations, which undermines transparency, accountability, and controllability of user impact—leading to diminished trust, misaligned intentions, and weak awareness of consequences. This work proposes a system-level framework that structures dialog behavior through explicit interaction constraints, such as guidance strategies, explanation styles, directness levels, and user control mechanisms, replacing conventional implicit prompt tuning. Built upon a modular architecture, the framework enables controllable generation, configurable interaction policies, and user-centered evaluation, thereby delivering transparent, auditable, and well-being-oriented recommendations. Empirical results demonstrate that this approach significantly enhances users’ self-efficacy, perceived autonomy, and appropriate reliance on system advice.

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.

Problem

• trustworthy AI
• wellbeing recommendation
• controllable interaction
• LLM-based systems
• user agency

Innovation

• controllable LLM
• wellbeing recommendation
• interaction constraints
• trust calibration
• user agency