Skip to Main Content

STORM from Stanford University This link opens in a new window
STORM from Stanford University

Alt Names:
Co-STORM
Keywords:
Stanford, RAG, research, writing
Subjects:
Research, Architecture and built environment, Business and management, Communication and creative media, Health sciences and medicine, International relations and humanities, Social sciences, psychology and counselling
Data type:
Text
Licensing:
Check site for trials, plans and options
Purpose:
Learning, Reading and writing
Type:
Web application

Description

STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking) is a research project from Stanford University designed to generate long, grounded, Wikipedia-like articles from scratch. It focuses on the pre-writing stage by discovering diverse perspectives, simulating conversations with topic experts, and curating collected information to create comprehensive outlines. This system aims to improve the breadth and depth of articles, making them well-organised and informative.

Artificial intelligence features

  • Perspective-guided questions: Generates questions from diverse perspectives to enhance the breadth and depth of content
  • Simulated conversations: Mimics expert discussions to gather comprehensive information on a topic
  • RAG (retrieval-augmented generation): Uses retrieval techniques to source information from trusted internet sources
  • Outline creation: Curates collected information to create detailed and organised outlines
  • Evaluation metrics: Assesses the quality of pre-writing stages to ensure well-organised and informative articles

title
Loading...