AI BENCHMARK PROFILE

EMPATH

General AISafety & Trustworthiness

EMPATH evaluates safety of emotional-support chatbots via auditor-generated multi-turn conversations scored on 19 metrics across crisis handling, therapeutic quality, conversational integrity, emotional safety, and cultural adaptation.

Released: 2026-06-29
Readiness: Paper only
Primary field: General AI

Why it matters

Safety evaluation for emotional-support chatbots needs multilingual, multi-turn metrics; EMPATH appears to address that gap.

Motivation

Safety benchmarks often buy scalability by fixing the prompt, the language, and the turn structure.

Primary resources

Paper ↗Hugging Face ↗

Benchmark Radar records only publicly supported details and links back to primary sources for verification.