Towards Healthy AI: Large Language Models Need Therapists Too
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Recent advances in large language models (LLMs) have led to the development of powerful chatbots capable of engaging in fluent human-like conversations.However, these chatbots may be harmful, exhibiting manipulation, gaslighting, narcissism, and other toxicity.To work toward safer and more well-adjusted models, we propose a framework that uses psychotherapy to identify and mitigate harmful chatbot behaviors.The framework involves four different artificial intelligence (AI) agents: the Chatbot whose behavior is to be adjusted, a User, a Therapist, and a Critic that can be paired with reinforcement learning-based LLM tuning.We illustrate the framework with a working example of a social conversation involving four instances of ChatGPT, showing that the framework may mitigate the toxicity in conversations between LLM-driven chatbots and people.Although there are still several challenges and directions to be addressed in the future, the proposed framework is a promising approach to improving the alignment between LLMs and human values.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Concrete Problems in AI Safety
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016) · arXiv · doi:10.48550/arxiv.1606.06565 · Cited by 1,314
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2020) · arXiv · doi:10.48550/arxiv.2004.09456 · Cited by 643
Ethical and social risks of harm from Language Models
Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.-S., Cheng, M., Glaese, M., Balle, B., Kasirzadeh, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.04359 · Cited by 477
The Ghost in the Machine has an American accent: value conflict in GPT-3
Johnson, R. L., Pistilli, G., Menédez-González, N., Duran, L. D. D., Panai, E., Kalpokiene, J., & Bertulfo, D. J. (2022) · arXiv · doi:10.48550/arxiv.2203.07785 · Cited by 50
Zhuang, S., & Hadfield-Menell, D. (2021) · arXiv · doi:10.48550/arxiv.2102.03896 · Cited by 22
Cited by
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage
Hadi, M. U., tashi, Q. A., Qureshi, R., Shah, A., muneer, A., Irfan, M., Zafar, A., Shaikh, M. B., Akhtar, N., Wu, J., et al. (2023) · doi:10.36227/techrxiv.23589741.v1 · Cited by 370
ChatGPT and Bard exhibit spontaneous citation fabrication during psychiatry literature search
McGowan, A., Gui, Y., Dobbs, M., Shuster, S., Cotter, M., Selloni, A., Goodman, M., Srivastava, A., Cecchi, G. A., & Corcoran, C. M. (2023) · Psychiatry Research · doi:10.1016/j.psychres.2023.115334 · Cited by 140
Self-citationFerrario, A., Sedlakova, J., & Trachsel, M. (2024) · JMIR Mental Health · doi:10.2196/56569 · Cited by 61
Metadata
- Authors
- Lin, B., Bouneffouf, D., Cecchi, G., & Varshney, K.
- Venue
- Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)
- Published
- 2024
- Pages
- 61-70
- OpenAlex
- W4401043186
- Cited by
- 28
- References
- 5
- FWCI
- 8.91
- Type
- conference paper
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards Healthy AI: Large Language Models Need Therapists Too. https://app.cochat.ai/papers/10.18653/v1/2024.trustnlp-1.6
- The paper
- Lin, B., Bouneffouf, D., Cecchi, G., & Varshney, K. (2024). Towards Healthy AI: Large Language Models Need Therapists Too. Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024). https://doi.org/10.18653/v1/2024.trustnlp-1.6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.