Benchmark construction artifacts in hallucination detection corpora allow naive text-similarity baselines to achieve near-perfect scores, and controlled evaluations show most methods perform near chance except SAPLMA and the new DRIFT probe.
arXiv preprint arXiv:2507.02990 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
LLM safety guardrails fail for most mental health conditions with up to 100% failure rates for eating disorders, substance use disorder, and major depressive disorder, while holding only for suicide and self-harm.
VERA-MH proposes an automated pipeline using simulated conversations and a rubric to evaluate AI chatbots on suicide risk handling in mental health contexts.
citing papers explorer
-
PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts
Benchmark construction artifacts in hallucination detection corpora allow naive text-similarity baselines to achieve near-perfect scores, and controlled evaluations show most methods perform near chance except SAPLMA and the new DRIFT probe.
-
One Year Later...The Harms Persist, But So Do We!
LLM safety guardrails fail for most mental health conditions with up to 100% failure rates for eating disorders, substance use disorder, and major depressive disorder, while holding only for suicide and self-harm.
-
VERA-MH Concept Paper
VERA-MH proposes an automated pipeline using simulated conversations and a rubric to evaluate AI chatbots on suicide risk handling in mental health contexts.