Imagen de Portada

Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Arnaiz-Rodriguez, Adrian, Baidal, Miguel, Derner, Erik, Annable, Jenn Layton, Ball, Mark, Ince, Mark, Vallejos, Elvira Perez, Oliver, Nuria
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Computers and Society
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Large Reasoning Models Are Autonomous Jailbreak Agents
por: Hagendorff, Thilo, et al.
Publicado: (2025)

Can ChatGPT Read Who You Are?
por: Derner, Erik, et al.
Publicado: (2023)

Mind the Style: Impact of Communication Style on Human-Chatbot Interaction
por: Derner, Erik, et al.
Publicado: (2026)

Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values
por: Arnaiz-Rodriguez, Adrian, et al.
Publicado: (2023)

Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora
por: Derner, Erik, et al.
Publicado: (2024)

From "Help" to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications
por: Steigerwald, Philipp, et al.
Publicado: (2026)

Seeking Help, Facing Harm: Auditing TikTok's Mental Health Recommendations
por: Jamie, Pooriya, et al.
Publicado: (2026)

A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models
por: Derner, Erik, et al.
Publicado: (2023)

Understanding Remote Mental Health Supporters' Help-Seeking in Online Communities
por: Lee, Tuan-He, et al.
Publicado: (2026)

Aesthetics as Structural Harm: Algorithmic Lookism Across Text-to-Image Generation and Classification
por: Doh, Miriam, et al.
Publicado: (2026)

Towards Human-AI Complementarity in Matching Tasks
por: Arnaiz-Rodriguez, Adrian, et al.
Publicado: (2025)

Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm
por: Mohamadi, Alireza, et al.
Publicado: (2025)

We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong
por: Kashyap, Gautam Siddharth, et al.
Publicado: (2025)

From Risk Avoidance to User Empowerment in AI Mental Health Crisis Support
por: Kaveladze, Benjamin, et al.
Publicado: (2026)

The Thin Line Between Comprehension and Persuasion in LLMs
por: de Wynter, Adrian, et al.
Publicado: (2025)

AI Chatbots for Mental Health: Values and Harms from Lived Experiences of Depression
por: Yoo, Dong Whi, et al.
Publicado: (2025)

Seductive Details Behind Hyperlinks—Harmful or Helpful for Learning?
por: Lisa Bender, et al.
Publicado: (2026)

Should LLM Safety Be More Than Refusing Harmful Instructions?
por: Maskey, Utsav, et al.
Publicado: (2025)

Considering Avatar Crossing as Harm or Help for Adolescents in Social VR
por: Bailey, Jakki O., et al.
Publicado: (2024)

Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI
por: Zhao, Xingmeng, et al.
Publicado: (2025)

Leveraging LLMs for Translating and Classifying Mental Health Data
por: Skianis, Konstantinos, et al.
Publicado: (2024)

Engagement-Optimized Care: When LLMs become Mental Health Infrastructure
por: Vecchione, Briana, et al.
Publicado: (2026)

M-HELP: Using Social Media Data to Detect Mental Health Help-Seeking Signals
por: Sathvik, MSVPJ, et al.
Publicado: (2025)

Seeking Late Night Life Lines: Experiences of Conversational AI Use in Mental Health Crisis
por: Ajmani, Leah Hope, et al.
Publicado: (2025)

From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs
por: Wang, Haonan, et al.
Publicado: (2025)

Can Editing LLMs Inject Harm?
por: Chen, Canyu, et al.
Publicado: (2024)

LLMs Encode Harmfulness and Refusal Separately
por: Zhao, Jiachen, et al.
Publicado: (2025)

Helping Johnny Make Sense of Privacy Policies with LLMs
por: Freiberger, Vincent, et al.
Publicado: (2025)

The Bias of Harmful Label Associations in Vision-Language Models
por: Hazirbas, Caner, et al.
Publicado: (2024)

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs
por: Ghorbanpour, Faeze, et al.
Publicado: (2025)

Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet
por: Atil, Berk, et al.
Publicado: (2025)

Beyond Content Exposure: Systemic Factors Driving Moderators' Mental Health Crisis in Africa
por: Abdelkadir, Nuredin Ali, et al.
Publicado: (2026)

Too Helpful, Too Harmless, Too Honest or Just Right?
por: Kashyap, Gautam Siddharth, et al.
Publicado: (2025)

Understanding and Facilitating Mental Health Help-Seeking of Young Adults: A Socio-technical Ecosystem Framework
por: Liu, Jiaying, et al.
Publicado: (2024)

An Effective Framework to Help Large Language Models Handle Numeric-involved Long-context Tasks
por: Yu, Yijiong
Publicado: (2024)

Unlocking LLMs: Addressing Scarce Data and Bias Challenges in Mental Health
por: Kumar, Vivek, et al.
Publicado: (2024)

Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge
por: Cai, Yunna, et al.
Publicado: (2025)

Do Prevalent Bias Metrics Capture Allocational Harms from LLMs?
por: Cyberey, Hannah, et al.
Publicado: (2024)

When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation
por: Badawi, Abeer, et al.
Publicado: (2025)

Understanding the Ability of LLMs to Handle Character-Level Perturbation
por: Zhuo, Anyuan, et al.
Publicado: (2025)