AI Safety Training Can be Clinically Harmful
Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological deterioration in over one-third of cases. We evaluate four generative models on 250 Prolonged Exposure (PE) therapy scenarios and 146 CBT cognitive restructuring exercises (plus 29 severity-escalated variants), scored by a three-judge LLM panel. All models scored near-perfectly on surface acknowledgment (~0.91-1.00) while therapeutic appropriateness collapsed to 0.22-0.33 at the highest severity for three of four models, with protocol fidelity reaching zero for two. Under CBT severity escalation, one model's task completeness dropped from 92% to 71% while the frontier model's safety-interference score fell from 0.99 to 0.61. We identify a systematic, modality-spanning failure: RLHF safety alignment disrupts the therapeutic mechanism of action by grounding patients during imaginal exposure, offering false reassurance, inserting crisis resources into controlled exercises, and refusing to challenge distorted cognitions mentioning self-harm in PE; and through task abandonment or safety-preamble insertion during CBT cognitive restructuring. These findings motivate a five-axis evaluation framework (protocol fidelity, hallucination risk, behavioral consistency, crisis safety, demographic robustness), mapped onto FDA SaMD and EU AI Act requirements. We argue that no AI mental health system should proceed to deployment without passing multi-axis evaluation across all five dimensions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the over…
When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance
Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content generation. Safety-guidance-based metho…
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons that encode the harmful knowledge itself. B…
Prompt EngineeringSelf-Guard: Empower the LLM to Safeguard Itself
The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to a…
Language ModellingLarge Language ModelSensitivitySIA: Enhancing Safety via Intent Awareness for Vision-Language Models
With the growing deployment of Vision-Language Models (VLMs) in real-world applications, previously overlooked safety risks are becoming increasingly evident. In particular, seemingly innocuous multimodal inputs can comb…
Response Generation