COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling

TL;DR

This paper introduces QUORUM, a comprehensive evaluation framework, and COACH, a LLM-driven pipeline, to develop and assess personalized health counselling systems that integrate user, expert, and developer perspectives.

Contribution

It presents a unified evaluation framework for stakeholder perspectives and a LLM-based pipeline for personalized health counselling in a real-world health app context.

Findings

Stakeholders agree on relevance and quality of counselling.

Divergence exists in tone and error sensitivity.

Multi-stakeholder evaluation enhances trustworthiness.

Abstract

Systems that collect data on sleep, mood, and activities can provide valuable lifestyle counselling to populations affected by chronic disease and its consequences. Such systems are, however, challenging to develop; besides reliably extracting patterns from user-specific data, systems should also contextualise these patterns with validated medical knowledge to ensure the quality of counselling, and generate counselling that is relevant to a real user. We present QUORUM, a new evaluation framework that unifies these developer-, expert-, and user-centric perspectives, and show with a real case study that it meaningfully tracks convergence and divergence in stakeholder perspectives. We also present COACH, a Large Language Model-driven pipeline to generate personalised lifestyle counselling for our Healthy Chronos use case, a diary app for cancer patients and survivors. Applying our framework shows that overall, users, medical experts, and developers converge on the opinion that the generated counselling is relevant, of good quality, and reliable. However, stakeholders also diverge on the tone of the counselling, sensitivity to errors in pattern-extraction, and potential hallucinations. These findings highlight the importance of multi-stakeholder evaluation for consumer health language technologies and illustrate how a unified evaluation framework can support trustworthy, patient-centered NLP systems in real-world settings.