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

• URL: http://arxiv.org/abs/2402.12738v1
• Date: Tue, 20 Feb 2024 06:05:36 GMT
• Title: Can Large Language Models be Used to Provide Psychological Counselling? An Analysis of GPT-4-Generated Responses Using Role-play Dialogues
• Authors: Michimasa Inaba, Mariko Ukiyo and Keiko Takamizo
• Abstract summary: Mental health care poses an increasingly serious challenge to modern societies. This study collected counseling dialogue data via role-playing scenarios involving expert counselors. Third-party counselors evaluated the appropriateness of responses from human counselors and those generated by GPT-4 in identical contexts.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations [58.65755268815283]
  Many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion. We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations. Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.
  arXiv  Detail & Related papers  (2024-11-07T21:37:51Z)
• Enhancing AI-Driven Psychological Consultation: Layered Prompts with Large Language Models [44.99833362998488]
  We explore the use of large language models (LLMs) like GPT-4 to augment psychological consultation services. Our approach introduces a novel layered prompting system that dynamically adapts to user input. We also develop empathy-driven and scenario-based prompts to enhance the LLM's emotional intelligence.
  arXiv  Detail & Related papers  (2024-08-29T05:47:14Z)
• Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting [46.919537239016734]
  Large language models (LLMs) have simplified the implementation of multi-turn dialogues. It remains challenging to deliver satisfactory performance in low-resource domain, like psychological dialogue dialogue. We propose a knowledge-driven progressive thought prompting method to guide LLM to generate psychology-related dialogue.
  arXiv  Detail & Related papers  (2024-06-24T12:02:56Z)
• CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling [27.193022503592342]
  We propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues. A comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations.
  arXiv  Detail & Related papers  (2024-05-26T05:18:00Z)
• Response Generation for Cognitive Behavioral Therapy with Large Language Models: Comparative Study with Socratic Questioning [6.400704401007114]
  This study investigates the impact of generated responses on subjective evaluations such as mood change, cognitive change, and dialogue quality. When using GPT-4, the amount of mood change, empathy, and other dialogue qualities improve significantly.
  arXiv  Detail & Related papers  (2024-01-29T08:53:41Z)
• K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learning [83.19215082550163]
  We propose K-ESConv, a novel prompt learning based knowledge injection method for emotional support dialogue system. We evaluate our model on an emotional support dataset ESConv, where the model retrieves and incorporates knowledge from external professional emotional Q&A forum.
  arXiv  Detail & Related papers  (2023-12-16T08:10:10Z)
• ChatCounselor: A Large Language Models for Mental Health Support [8.639639227401625]
  ChatCounselor is a large language model (LLM) solution designed to provide mental health support. The training dataset, Psych8k, was constructed from 260 in-depth interviews, each spanning an hour. ChatCounselor surpasses existing open-source models in the counseling Bench and approaches the performance level of ChatGPT.
  arXiv  Detail & Related papers  (2023-09-27T07:57:21Z)
• FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems [53.89014188309486]
  We present a flexible neural framework that can integrate contextual information from multiple channels. We evaluate our model on the MSDialog dataset widely used for evaluating conversational response ranking tasks.
  arXiv  Detail & Related papers  (2023-03-31T23:58:28Z)
• Response-act Guided Reinforced Dialogue Generation for Mental Health Counseling [25.524804770124145]
  We present READER, a dialogue-act guided response generator for mental health counseling conversations. READER is built on transformer to jointly predict a potential dialogue-act d(t+1) for the next utterance (aka response-act) and to generate an appropriate response u(t+1) We evaluate READER on HOPE, a benchmark counseling conversation dataset.
  arXiv  Detail & Related papers  (2023-01-30T08:53:35Z)
• Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations [15.230185998553159]
  We develop a novel dataset, named HOPE, to provide a platform for the dialogue-act classification in counselling conversations. We collect 12.9K utterances from publicly-available counselling session videos on YouTube, extract their transcripts, clean, and annotate them with DAC labels. We propose SPARTA, a transformer-based architecture with a novel speaker- and time-aware contextual learning for the dialogue-act classification.
  arXiv  Detail & Related papers  (2021-11-12T10:30:30Z)
• Attention over Parameters for Dialogue Systems [69.48852519856331]
  We learn a dialogue system that independently parameterizes different dialogue skills, and learns to select and combine each of them through Attention over Parameters (AoP) The experimental results show that this approach achieves competitive performance on a combined dataset of MultiWOZ, In-Car Assistant, and Persona-Chat.
  arXiv  Detail & Related papers  (2020-01-07T03:10:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.