mlsanityData to 7 Oct 2026

Towards Healthy AI: Large Language Models Need Therapists Too

arXiv 2304.00416 ↗First posted 2 Apr 2023cs.AI cs.CL cs.CYcited by 13

Not on the map. Why?

Abstract (arXiv)

Recent advances in large language models (LLMs) have led to the development of powerful AI chatbots capable of engaging in natural and human-like conversations. However, these chatbots can be potentially harmful, exhibiting manipulative, gaslighting, and narcissistic behaviors. We define Healthy AI to be safe, trustworthy and ethical. To create healthy AI systems, we present the SafeguardGPT framework that uses psychotherapy to correct for these harmful behaviors in AI chatbots. The framework involves four types of AI agents: a Chatbot, a "User," a "Therapist," and a "Critic." We demonstrate the effectiveness of SafeguardGPT through a working example of simulating a social conversation. Our results show that the framework can improve the quality of conversations between AI chatbots and humans. Although there are still several challenges and directions to be addressed in the future, SafeguardGPT provides a promising approach to improving the alignment between AI chatbots and human values. By incorporating psychotherapy and reinforcement learning techniques, the framework enables AI chatbots to learn and adapt to human preferences and values in a safe and ethical way, contributing to the development of a more human-centric and responsible AI.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 29 of its 66 references that are in the map. First posted on arXiv 2 Apr 2023.

Builds on

29 of 66 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  4. 2017Deep reinforcement learning from human preferencescited by 3,846
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  6. 2020Learning to summarize from human feedbackcited by 2,562
  7. 2016Concrete Problems in AI Safetycited by 1,582
  8. 2022Red Teaming Language Models with Language Modelscited by 983
  9. 2021Ethical and social risks of harm from Language Modelscited by 957
  10. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  11. 2022Using cognitive psychology to understand GPT-3cited by 389
  12. 2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 298
17 more
  1. 2021MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcarecited by 159
  2. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  3. 2021Consequences of Misaligned AIcited by 79
  4. 2016On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Productscited by 52
  5. 2021GPT3-to-plan: Extracting plans from text using GPT-3cited by 26
  6. 2021Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learningcited by 16
  7. 2022Deep Annotation of Therapeutic Working Alliance in Psychotherapycited by 14
  8. 2022Neural Topic Modeling of Psychotherapy Sessionscited by 13
  9. 2022Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlookcited by 10
  10. 2022Working Alliance Transformer for Psychotherapy Dialogue Classificationcited by 9
  11. 2019Split Q Learning: Reinforcement Learning with Two-Stream Rewardscited by 8
  12. 2022SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learningcited by 8
  13. 2023Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamicscited by 6
  14. 2017Detecting Egregious Conversations between Customers and Virtual Agentscited by 4
  15. 2022Computational Inference in Cognitive Science: Operational, Societal and Ethical Considerationscited by 4
  16. 2023TherapyView: Visualizing Therapy Sessions with Temporal Topic Modeling and AI-Generated Artscited by 3
  17. 2018A Psychopathological Approach to Safety Engineering in AI and AGIcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 2; 2026: 2.

13 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 147
  3. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  4. 2023chatClimate: Grounding Conversational AI in Climate Sciencecited by 32
  5. 2024Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementationcited by 27
  6. 2024Large Language Model for Mental Health: A Systematic Reviewcited by 14
  7. 2024Metacognitive Myopia in Large Language Modelscited by 6
  8. 2025FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Healthcited by 5
  9. 2023Is There Any Social Principle for LLM-Based Agents?cited by 4
  10. 2024Enhancing Psychotherapy Counseling: A Data Augmentation Pipeline Leveraging Large Language Models for Counseling Conversationscited by 3
  11. 2025Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directionscited by 3
  12. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
1 more
  1. 2026On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignmentcited by 0