"You tell me": A Dataset of GPT-4-Based Behaviour Change Support Conversations
This provides a resource for researchers and developers working on conversational agents for mental health, though it is incremental as it focuses on data collection rather than new methods.
The authors tackled the lack of user behavior data in LLM-based mental health interventions by creating a dataset of GPT-4 conversations for behavior change, including user interactions, language analysis, and feedback to inform system design.
Conversational agents are increasingly used to address emotional needs on top of information needs. One use case of increasing interest are counselling-style mental health and behaviour change interventions, with large language model (LLM)-based approaches becoming more popular. Research in this context so far has been largely system-focused, foregoing the aspect of user behaviour and the impact this can have on LLM-generated texts. To address this issue, we share a dataset containing text-based user interactions related to behaviour change with two GPT-4-based conversational agents collected in a preregistered user study. This dataset includes conversation data, user language analysis, perception measures, and user feedback for LLM-generated turns, and can offer valuable insights to inform the design of such systems based on real interactions.