{
  "id": 7486888,
  "title": "K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations",
  "url": "https://urgent.news/2026/09/14/k-bench-a-clinically-calibrated-benchmark-for-evaluating-large",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-14T16:49:23.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.15855v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "% !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conversations remains poorly characterised. We developed K-Bench, a clinician-calibrated, protected benchmark evaluating 125 model configurations representing 33 base models from 14 providers across a fixed cohort of 200 multi-turn vignettes involving…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}