Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots
cs.AI, cs.CL, cs.LG
Submitted: 2025-09-19
Updated: 2026-01-20
Terminology
Sources
- Reinforcement Learning for LLM Post-Training: A Survey
- Foundational Challenges in Assuring Alignment and Safety of Large Language Models
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Constitutional AI: Harmlessness from AI Feedback
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Specific versus General Principles for Constitutional AI
- Building Guardrails for Large Language Models
- How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers
- The Llama 3 Herd of Models
- Aligner: Efficient Alignment by Learning to Correct
- Building Trust in Mental Health Chatbots: Safety Metrics and LLM-Based Evaluation Tools
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems