Reproduce “Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy” 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
Mengxi Xiao, Jingjing Chen, Ziyan Kuang, Jiarong Song, Wenhao Zhao, Zuchen Han, Yihuai Xu, Xiyang Huang and 7 more
Pandora simulates psychotherapy clients by planning both response content and expression. It updates psychological and relational conditions, forms an interpretation, plans purpose, and guides wording with a client-specific language profile. Across 115 cases, adding expression planning raised content-reduced expression similarity from 0.458 to 0.566 and lowered AI-like ratings from 35.6% to 7.2%; these findings concern simulation fidelity, not clinical outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.