Imagen de Portada

Mental Health AI Safety Claims Must Preserve Temporal Evidence

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dutta, Srimonti, Kandala, Ratna
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue
por: Kandala, Ratna, et al.
Publicado: (2026)

"What if she doesn't feel the same?" What Happens When We Ask AI for Relationship Advice
por: Manchanda, Niva, et al.
Publicado: (2025)

The Nonverbal Gap: Toward Affective Computer Vision for Safer and More Equitable Online Dating
por: Kandala, Ratna, et al.
Publicado: (2026)

Position: AI Safety Must Embrace an Antifragile Perspective
por: Jin, Ming, et al.
Publicado: (2025)

Safety Must Precede the Deployment of Open-Ended AI
por: Sheth, Ivaxi, et al.
Publicado: (2025)

AI Must not be Fully Autonomous
por: Adewumi, Tosin, et al.
Publicado: (2025)

VERA-MH: Reliability and Validity of an Open-Source AI Safety Evaluation in Mental Health
por: Bentley, Kate H., et al.
Publicado: (2026)

Cross-Lingual Mental Health Ontologies for Indian Languages: Bridging Patient Expression and Clinical Understanding through Explainable AI and Human-in-the-Loop Validation
por: Kandala, Ananth, et al.
Publicado: (2025)

HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking
por: Vladika, Juraj, et al.
Publicado: (2023)

Conjoined Predication and Scalar Implicature
por: Kandala, Ratna
Publicado: (2025)

Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support
por: Bandara, Eranga, et al.
Publicado: (2026)

Expert Evaluation and the Limits of Human Feedback in Mental Health AI Safety Testing
por: Jafari, Kiana, et al.
Publicado: (2026)

Trustworthy AI Must Account for Interactions
por: Cresswell, Jesse C.
Publicado: (2025)

Towards Privacy-Preserving Mental Health Support with Large Language Models
por: Xue, Dong, et al.
Publicado: (2026)

An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations
por: Nelson, Benjamin W., et al.
Publicado: (2025)

Dharma, Data and Deception: An LLM-Powered Rhetorical Analysis of Cow-Urine Health Claims on YouTube
por: Munir, Sheza, et al.
Publicado: (2026)

AI Must Embrace Specialization via Superhuman Adaptable Intelligence
por: Goldfeder, Judah, et al.
Publicado: (2026)

Responsible Evaluation of AI for Mental Health
por: Arnaout, Hiba, et al.
Publicado: (2026)

Position: AI Will Transform Neuropsychology Through Mental Health Digital Twins for Dynamic Mental Health Care, Especially for ADHD
por: Natarajan, Neil, et al.
Publicado: (2025)

Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
por: Lin, Zezheng, et al.
Publicado: (2026)

From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening
por: Kandala, Ratna, et al.
Publicado: (2025)

The Cost-Benefit of Interdisciplinarity in AI for Mental Health
por: Drakos, Katerina, et al.
Publicado: (2025)

Parallax: Why AI Agents That Think Must Never Act
por: Fokou, Joel
Publicado: (2026)

Enterprise AI Must Enforce Participant-Aware Access Control
por: Bhatt, Shashank Shreedhar, et al.
Publicado: (2025)

Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\rightarrow$ Evidence Reasoning
por: Javaji, Shashidhar Reddy, et al.
Publicado: (2025)

LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim Verification
por: Wang, Siyuan, et al.
Publicado: (2025)

NeurIPS Should Require Reproducibility Standards for Frontier AI Safety Claims
por: Vishwarupe, Varad, et al.
Publicado: (2026)

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
por: Qiu, Jiahao, et al.
Publicado: (2025)

Generative AI and Two-Tiered Online Mental Health Communities
por: Zhang, Manyang, et al.
Publicado: (2026)

VERA-MH: Validation of Ethical and Responsible AI in Mental Health
por: Belli, Luca, et al.
Publicado: (2026)

Position: State-of-the-Art Claims Require State-of-the-Art Evidence
por: Oh, YongKyung
Publicado: (2026)

Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG
por: Di Gioia, Davide
Publicado: (2026)

Pix2Gif: Motion-Guided Diffusion for GIF Generation
por: Kandala, Hitesh, et al.
Publicado: (2024)

Harnessing AI Agents to Advance Research on Refugee Child Mental Health
por: Shrivastava, Aditya, et al.
Publicado: (2025)

A Comprehensive Review of Datasets for Clinical Mental Health AI Systems
por: Mandal, Aishik, et al.
Publicado: (2025)

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
por: Seth, Pratinav, et al.
Publicado: (2026)

NGENT: Next-Generation AI Agents Must Integrate Multi-Domain Abilities to Achieve Artificial General Intelligence
por: Li, Zhicong, et al.
Publicado: (2025)

A Case for Leveraging Generative AI to Expand and Enhance Training in the Provision of Mental Health Services
por: Lawrence, Hannah R., et al.
Publicado: (2025)

Accelerate Creation of Product Claims Using Generative AI
por: Liang, Po-Yu, et al.
Publicado: (2025)

Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots
por: Lyu, Chenhan, et al.
Publicado: (2025)