Reproduce “Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yi Feng, Jiaqi Wang, Wenxuan Zhang, Zhuang Chen, Yutong Shen, Xiyao Xiao, Minlie Huang, Liping Jing and 1 more
Researchers developed an Interactive Narrative Therapist (INT) framework, powered by large language models, which simulates structured narrative therapy and guides clients through progressive stages of reflection. An Innovative Moment Assessment (IMA) quantitatively tracks therapeutic progress by identifying narrative shifts in client utterances, showing the INT system outperforms generic LLM-based approaches in fostering deeper therapeutic engagement.
Key insights
- Expert therapeutic interactions can be formalized into progressive stages and reflection levels, enabling LLMs to computationally plan and guide structured conversations.
- Quantifying "Innovative Moments" in client speech provides a clinically meaningful and objective method to measure therapeutic progression and depth of narrative transformation.
- Incorporating structured, theory-driven psychotherapeutic principles into LLM design leads to more effective and profound AI-driven mental health support than generic emotional assistance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.