Reproduce “Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts” 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
Mounica Maddela, Megan Ung, Jing Xu, Andrea Madotto, Heather Foran, Y-Lan Boureau
PatternReframe builds a crowdsourced dataset of thoughts and reframings conditioned on personas and ten named CBT thought patterns. It evaluates models on generating, classifying, and reframing examples. In human ratings on a 100-item test sample, all evaluated models exceeded 70% on removing the specified pattern, with GPT-3.5 best. These task-level ratings do not establish learning or clinical benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.