Measuring Risk, Not Harm: Detecting Psychological Harm Risk Factors in LLM Conversations
cs.CL, cs.CY
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/responsibleai/ASSERT
Terminology
Sources
- DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs
- Illusions of Intimacy: How Emotional Dynamics Shape Human-AI Relationships
- Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- How AI and Human Behaviors Shape Psychosocial Effects of Extended Chatbot Use: A Longitudinal Randomized Controlled Study
- AI red-teaming is a sociotechnical problem: on values, labor, and harms
- Automating Deception: Scalable Multi-Turn LLM Jailbreaks
- Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
- DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots
- Anthropomorphism in AI Companion Communities: Age, Gender, and Emotional Correlates
- AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety
- Psychological Influences of Conversational AI: Research and Design Directions for Reducing Harm and Promoting Well-Being
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data