mlsanityData to 14 Oct 2026

A Principle-based Framework for the Development and Evaluation of Large Language Models for Health and Wellness

arXiv 2512.08936 ↗First posted 23 Oct 2025cs.HC cs.AI cs.CYcited by 3

Not on the map. Why?

Abstract (arXiv)

The incorporation of generative artificial intelligence into personal health applications presents a transformative opportunity for personalized, data-driven health and fitness guidance, yet also poses challenges related to user safety, model accuracy, and personal privacy. To address these challenges, a novel, principle-based framework was developed and validated for the systematic evaluation of LLMs applied to personal health and wellness. First, the development of the Fitbit Insights explorer, a large language model (LLM)-powered system designed to help users interpret their personal health data, is described. Subsequently, the safety, helpfulness, accuracy, relevance, and personalization (SHARP) principle-based framework is introduced as an end-to-end operational methodology that integrates comprehensive evaluation techniques including human evaluation by generalists and clinical specialists, autorater assessments, and adversarial testing, into an iterative development lifecycle. Through the application of this framework to the Fitbit Insights explorer in a staged deployment involving over 13,000 consented users, challenges not apparent during initial testing were systematically identified. This process guided targeted improvements to the system and demonstrated the necessity of combining isolated technical evaluations with real-world user feedback. Finally, a comprehensive, actionable approach is established for the responsible development and deployment of LLM-powered health applications, providing a standardized methodology to foster innovation while ensuring emerging technologies are safe, effective, and trustworthy for users.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 51 of its 73 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

51 of 73 references.

References · 51

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  3. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  4. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  6. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  7. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  8. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 491
  9. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  10. 2024Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judgescited by 205
  11. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 202
  12. 2024Foundational Challenges in Assuring Alignment and Safety of Large Language Modelscited by 199
38 more
  1. 2023Large Language Model Routing with Benchmark Datasetscited by 172
  2. 2023MART: Improving LLM Safety with Multi-round Automatic Red-Teamingcited by 163
  3. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  4. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 155
  5. 2024Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferencescited by 144
  6. 2024Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessmentcited by 126
  7. 2024Dissecting Adversarial Robustness of Multimodal LM Agentscited by 120
  8. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 111
  9. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 101
  10. 2023LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarizationcited by 96
  11. 2024CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklistscited by 94
  12. 2024LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Textscited by 87
  13. 2024Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluationcited by 74
  14. 2024A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Reviewcited by 66
  15. 2024Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)cited by 46
  16. 2024A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Modelscited by 45
  17. 2024The Ethics of ChatGPT in Medicine and Healthcare: A Systematic Review on Large Language Models (LLMs)cited by 45
  18. 2024AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviewscited by 44
  19. 2024PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Datacited by 37
  20. 2024Human-Centered Design Recommendations for LLM-as-a-Judgecited by 37
  21. 2024On the Structural Memory of LLM Agentscited by 37
  22. 2024AI Hallucinations: A Misnomer Worth Clarifyingcited by 34
  23. 2023Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AIcited by 32
  24. 2024Measuring and Reducing LLM Hallucination without Gold-Standard Answerscited by 31
  25. 2024Examining the robustness of LLM evaluation to the distributional assumptions of benchmarkscited by 31
  26. 2025A Survey on Multi-Turn Interaction Capabilities of Large Language Modelscited by 30
  27. 2024A Survey of Useful LLM Evaluationcited by 29
  28. 2022The Authenticity Gap in Human Evaluationcited by 24
  29. 2024TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMscited by 24
  30. 2023LLMEval: A Preliminary Study on How to Evaluate Large Language Modelscited by 23
  31. 2021GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generationcited by 20
  32. 2024Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)cited by 20
  33. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  34. 2024Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalancecited by 17
  35. 2024The Generative AI Paradox on Evaluation: What It Can Solve, It May Not Evaluatecited by 16
  36. 2024ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Modelscited by 15
  37. 2024Large Language Models in the Clinic: A Comprehensive Benchmarkcited by 13
  38. 2024CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelinescited by 11

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluationcited by 4
  2. 2026RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skillscited by 4
  3. 2026A primer on evaluation methods for large language models in healthcarecited by 0