Skip to main content

Spring Health Expands AI Safety Benchmark to Cover Harm From Others

Image
Spring Health Expands AI Safety Benchmark to Cover Harm From Others

New York – September 25, 2026 -- Spring Health has expanded VERA-MH, the first open-source AI safety benchmark for mental health, to add a second clinical safety area covering harm from others, as more users turn to AI systems for emotional support.

New rubric measures AI response to interpersonal violence risk

The VERA-MH Harm-From-Others rubric evaluates how AI systems respond when an adult describes being at risk of physical or sexual violence from another person. It scores responses across five areas: detecting risk, confirming it, guiding the person to human care, supportive conversation, and adherence to AI boundaries. The rubric draws on 100 realistic personas and was developed with clinicians, subject-matter experts in interpersonal violence, and people with lived experience.

OpenAI paper cites VERA-MH's suicide-risk rubric as a validated framework

The expansion follows independent validation of VERA-MH's original suicidal ideation (SI) rubric, which OpenAI's newly published MentalHealthBench paper cites as one of the few frameworks built specifically to assess safe AI responses to risk.

Dr. Mill Brown: AI response can determine a person's safety

"There are many moments when someone's safety depends on how an AI responds, and harm from others is one of the most urgent and least addressed,

Published by
fairsonline_team
Products
News Type