# Can Large Language Models be Used to Provide Psychological Counselling? An Analysis of GPT-4-Generated Responses Using Role-play Dialogues

arXiv: https://arxiv.org/abs/2402.12738 · HTML: https://mlsanity.com/paper/2402.12738/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 5 of 5)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach](https://mlsanity.com/paper/2101.07714/) (2021)
- [PAL: Persona-Augmented Emotional Support Conversation Generation](https://mlsanity.com/paper/2212.09235/) (2022)
- [Improving the Generalizability of Depression Detection by Leveraging Clinical Questionnaires](https://mlsanity.com/paper/2204.10432/) (2022)

## Built on by (most cited first, 6 of 6)

- [KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained Counselors](https://mlsanity.com/paper/2506.01357/) (2025)
- [Enhancing Psychotherapy Counseling: A Data Augmentation Pipeline Leveraging Large Language Models for Counseling Conversations](https://mlsanity.com/paper/2406.08718/) (2024)
- [Optimizing Psychological Counseling with Instruction-Tuned Large Language Models](https://mlsanity.com/paper/2406.13617/) (2024)
- [UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models](https://mlsanity.com/paper/2410.14059/) (2024)
- [EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognition](https://mlsanity.com/paper/2506.19279/) (2025)
- [Beyond Reflection: Affirmation as a Promising Behavioral Marker Associated with Quality in Text-Based Counseling](https://mlsanity.com/paper/2608.26689/) (2026)

## Abstract (arXiv)

Mental health care poses an increasingly serious challenge to modern societies. In this context, there has been a surge in research that utilizes information technologies to address mental health problems, including those aiming to develop counseling dialogue systems. However, there is a need for more evaluations of the performance of counseling dialogue systems that use large language models. For this study, we collected counseling dialogue data via role-playing scenarios involving expert counselors, and the utterances were annotated with the intentions of the counselors. To determine the feasibility of a dialogue system in real-world counseling scenarios, third-party counselors evaluated the appropriateness of responses from human counselors and those generated by GPT-4 in identical contexts in role-play dialogue data. Analysis of the evaluation results showed that the responses generated by GPT-4 were competitive with those of human counselors.