Cover Image

AI Safety Training Can be Clinically Harmful

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	BN, Suhas, Sherrill, Andrew M., Arriaga, Rosa I., Wiese, Chris W., Abdullah, Saeed
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Computers and Society Machine Learning I.2.7; J.3; K.4.1; H.5.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations
by: BN, Suhas, et al.
Published: (2025)

The Pursuit of Empathy: Evaluating Small Language Models for PTSD Dialogue Support
by: BN, Suhas, et al.
Published: (2025)

Fine-Tuning Large Audio-Language Models with LoRA for Precise Temporal Localization of Prolonged Exposure Therapy Elements
by: BN, Suhas, et al.
Published: (2025)

When Large Language Models are More PersuasiveThan Incentivized Humans, and Why
by: Schoenegger, Philipp, et al.
Published: (2025)

How Real Are Synthetic Therapy Conversations? Evaluating Fidelity in Prolonged Exposure Dialogues
by: BN, Suhas, et al.
Published: (2025)

The Fragility Of Moral Judgment In Large Language Models
by: van Nuenen, Tom, et al.
Published: (2026)

AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations
by: Yun, Bhada, et al.
Published: (2026)

Documenting SME Processes with Conversational AI: From Tacit Knowledge to BPMN
by: Radhakrishnan, Unnikrishnan
Published: (2025)

Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild
by: Loth, Alexander, et al.
Published: (2026)

Can LLMs and humans be friends? Uncovering factors affecting human-AI intimacy formation
by: Hong, Yeseon, et al.
Published: (2025)

Qwerty AI: Explainable Automated Age Rating and Content Safety Assessment for Russian-Language Screenplays
by: Zmanovskii, Nikita
Published: (2025)

The Cultural Gene of Large Language Models: A Study on the Impact of Cross-Corpus Training on Model Values and Biases
by: Fenech-Borg, Emanuel Z., et al.
Published: (2025)

Superhuman Game AI Disclosure: Expertise and Context Moderate Effects on Trust and Fairness
by: Chua, Jaymari, et al.
Published: (2025)

Sample-Efficient Language Model for Hinglish Conversational AI
by: Singh, Sakshi, et al.
Published: (2025)

From Native Memes to Global Moderation: Cross-Cultural Evaluation of Vision-Language Models for Hateful Meme Detection
by: Wang, Mo, et al.
Published: (2026)

Building the Web for Agents: A Declarative Framework for Agent-Web Interaction
by: Schultze, Sven, et al.
Published: (2025)

Big Help or Big Brother? Auditing Tracking, Profiling, and Personalization in Generative AI Assistants
by: Vekaria, Yash, et al.
Published: (2025)

Functional Flexibility in Generative AI Interfaces: Text Editing with LLMs through Conversations, Toolbars, and Prompts
by: Lehmann, Florian, et al.
Published: (2024)

AI vs. Human Moderators: A Comparative Evaluation of Multimodal LLMs in Content Moderation for Brand Safety
by: Levi, Adi, et al.
Published: (2025)

Not Everything That Counts Can Be Counted: A Case for Safe Qualitative AI
by: Beltoft, Stine, et al.
Published: (2025)

How Adding Metacognitive Requirements in Support of AI Feedback in Practice Exams Transforms Student Learning Behaviors
by: Ahmad, Mak, et al.
Published: (2025)

Harmful Terms and Where to Find Them: Measuring and Modeling Unfavorable Financial Terms and Conditions in Shopping Websites at Scale
by: Tsai, Elisa, et al.
Published: (2025)

What Would GPT Click: Practical Effects of Human-AI Behavioral Misalignment and the Cost of Synthetic Participants in User Experience
by: Kuric, Eduard, et al.
Published: (2026)

"The Data Says Otherwise"-Towards Automated Fact-checking and Communication of Data Claims
by: Fu, Yu, et al.
Published: (2024)

The AI Memory Gap: Users Misremember What They Created With AI or Without
by: Zindulka, Tim, et al.
Published: (2025)

"I followed what felt right, not what I was told": Autonomy, Coaching, and Recognizing Bias Through AI-Mediated Dialogue
by: Taheri, Atieh, et al.
Published: (2026)

Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News
by: Loth, Alexander, et al.
Published: (2026)

Writer-Defined AI Personas for On-Demand Feedback Generation
by: Benharrak, Karim, et al.
Published: (2023)

Collaborative Document Editing with Multiple Users and AI Agents
by: Lehmann, Florian, et al.
Published: (2025)

Designing Transparent AI-Mediated Language Support for Intergenerational Family Communication
by: Kang, Sora, et al.
Published: (2026)

Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models
by: Young, Richard
Published: (2025)

Bye Bye Perspective API: Lessons for Measurement Infrastructure in NLP, CSS and LLM Evaluation
by: Hartmann, David, et al.
Published: (2026)

Whose wife is it anyway? Assessing bias against same-gender relationships in machine translation
by: Stewart, Ian, et al.
Published: (2024)

Distorted Perspectives of LLM-Simulated Preferences: Can AI Mislead Design?
by: Kuric, Eduard, et al.
Published: (2026)

ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant
by: Murzaku, John, et al.
Published: (2025)

Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype
by: Agustin, Matthew Christian
Published: (2026)

Know Your Author: Does the AI Penalty Hold in Short Fiction?
by: Todasco, Michael, et al.
Published: (2026)

Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Tools
by: Buschek, Daniel
Published: (2024)

Human Agency, Causality, and the Human Computer Interface in High-Stakes Artificial Intelligence
by: Hattab, Georges
Published: (2026)

Generative Confidants: How do People Experience Trust in Emotional Support from Generative AI?
by: Volpato, Riccardo, et al.
Published: (2026)