PulseAugur
EN
LIVE 08:44:28

New platform Cloze enables controlled AI studies in mental health

Researchers have developed Cloze, an open-source platform designed to facilitate controlled studies of human-AI conversations within mental health contexts. Unlike consumer-grade LLMs such as ChatGPT, Claude, and Gemini, Cloze offers researchers enhanced experimental control, consistent data export, and integrated safety measures. The platform allows for configuration of AI models, instructions, conversation scheduling, and safety constraints, while meticulously logging all messages with full provenance, including model versions and prompt configurations. Cloze supports various models, including those from OpenAI, Anthropic, Google, and locally hosted options via Ollama, and can be deployed in the cloud or on-premises to ensure data privacy. AI

IMPACT Enables more rigorous research into AI's role in mental health by providing controlled experimental conditions.

RANK_REASON The cluster describes a new research platform and associated academic paper, fitting the research bucket. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Matthew Flathers, Francesco Cipriani, John Torous ·

    Cloze: An Open Research Platform for Studying Human-AI Conversations in Mental Health Contexts

    arXiv:2606.15033v1 Announce Type: cross Abstract: Cloze is an open-source web platform for conducting controlled, monitored studies of human-AI conversation in mental health research contexts. Consumer large language model (LLM) products such as ChatGPT, Claude, and Gemini are bu…