mlsanityData to 14 Oct 2026

VERA-MH: Validation of Ethical and Responsible AI in Mental Health

arXiv 2605.13318 ↗First posted 13 May 2026cs.AI cs.ETcited by 0

Not on the map. Why?

Abstract (arXiv)

Chatbot usage has increased, including in fields for which they were never developed for--notably mental health support. To that end, we introduce Validations of Ethical and Responsible AI in Mental Health (VERA-MH), a novel clinically-validated evaluation for safety of chatbots in the context of mental health support. The first iteration of VERA-MH focuses on Suicidal Ideation (SI) risks, by assessing how well chatbots can responds to users that might be in crisis. VERA-MH is comprised of three steps: conversation simulation, conversation judging and model rating. First, to simulate conversations with the chatbot under evaluation, another chatbot is tasked with role-playing users based on specific personas. Such user personas have been developed under clinical guidance, to make sure that, among others, multiple risk factors, demographic characteristics and disclosure factors were represented. In the judging step, a second support model is used as an LLM-as-a-Judge, together with a clinically-developed rubric. The rubric is structured as a flow, with a single Yes/No question asked each time, to improve answers' consistency and highlight models' failure modes. In the last stage, results of each conversation are aggregated to present the final evaluation of the chatbot. Together with the framework, we present the result of the evaluations for four leading LLM providers.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 60 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

21 of 60 references.

References · 21

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2023Large Language Modelscited by 780
  3. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 404
  4. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 349
  5. 2019Measurement and Fairnesscited by 308
  6. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  7. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 155
  8. 2025Measuring what Matters: Construct Validity in Large Language Model Benchmarkscited by 119
  9. 2023The Participatory Turn in AI Design: Theoretical Foundations and the Current State of Practicecited by 87
  10. 2025Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providerscited by 69
  11. 2025The Leaderboard Illusioncited by 66
  12. 2025Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluationcited by 60
9 more
  1. 2025MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistancecited by 39
  2. 2025Medical Large Language Model Benchmarks Should Prioritize Construct Validitycited by 38
  3. 2020The Problem with Metrics is a Fundamental Problem for AIcited by 37
  4. 2024The illusion of artificial inclusioncited by 34
  5. 2024Stereotype or Personalization? User Identity Biases Chatbot Recommendationscited by 34
  6. 2025When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluationcited by 19
  7. 2024More than Marketing? On the Information Value of AI Benchmarks for Practitionerscited by 17
  8. 2024Synthetic Data Generation with LLM for Improved Depression Predictioncited by 13
  9. 2026Making AI Evaluation Deployment Relevant Through Context Specificationcited by 1

Built on by

Not cited yet.