Google's 56-author paper: training LLMs in simulation for psychiatric intake
SRSchmidgall · x · 2026-10-31
The thread concludes with paper links. 'Training language models in simulation for psychiatric intake' (arXiv:2610.40476) by Samuel Schmidgall and 55 co-authors spans Google DeepMind, Google Research, Google Health, and academic partners including Harvard, Stanford, UCLA, UCSF, Johns Hopkins, Penn, Yale, Columbia, and NYU.
Per the abstract, multi-turn RL in simulation improves LLM performance on structured text-based psychiatric intake across history-taking, differential diagnosis, and initial management planning, evaluated in a randomized double-blind crossover study (N=60 matched scenario pairs, 120 encounters). This thread is the paper's official walkthrough.
More from Research
- NVIDIA Nemotron 3.5 scales LLM self-verification, +9-10 points on agentic benchmarks — sarahcat21 · 2026-10-31
- Unofficial OpenTargets MCP Server Brings Gene-Drug-Disease Data to LLMs — modelcontextprotocol · 2026-10-31
- Researchers find 5 personality structures in LLM weight space, Big Five-like — luke_drago_ · 2026-10-31
- NVS benchmarks are misaligned: proper pose alignment puts 3D Gaussians back at SOTA — kwangmoo_yi · 2026-10-31
- arXiv moderator: submission surge causes months-long holds, new moderators wanted — tdietterich · 2026-10-31
- arXiv policy checks reject class projects, proposals, surveys and position papers — tdietterich · 2026-10-31