Papers/2611.21622
🧪 Test?View on arXiv

CrisisBench: an evaluation suite for crisis counseling AI

Not specified in the provided content

crisis counselingevaluation suiteprivacy-preservingLLM
2611.21622
Builder Relevance
70%
15h ago

Abstract

CrisisBench is a privacy-preserving evaluation suite for crisis counseling AI that addresses the limitations of existing benchmarks in capturing essential aspects of crisis conversations.

Reality Card

Core Claim

CrisisBench enables scalable, privacy-preserving evaluation of crisis counseling AI, revealing that current systems perform strongly on structural competencies but diverge from expert counselors on response-level failures.

Method / Result

In multi-turn evaluation, retrieval-augmented generation scored highest overall with a score of 0.961.

Limitations

The evaluation systems underperformed human counselors on excessive empathy and questioning, indicating a gap in response-level performance.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers