Stanford University’s STORM

STORM

Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking.

STORM is a LLM system that writes Wikipedia-like articles from scratch based on Internet search. Co-STORM further enhanced its feature by enabling human to collaborative LLM system to support more aligned and preferred information seeking and knowledge curation.

Stanford University’s STORM is an open-source AI research tool developed by the university’s Open Virtual Assistant Lab (OVAL). Launched in early 2024, STORM aims to assist researchers, students, and content creators in generating structured, well-researched, and cited long-form articles on various topics.

Read the published Paper.

Co-STORM

Co-STORM is an enhanced version of STORM that introduces collaboration. I can pick up a topic and examine it from multiple perspectives, such as those of a General Knowledge Provider, an expert, a historian, and even a moderator.

Co-STORM also maintains a dynamic, updated mind map, which organizes collected information into a hierarchical concept structure, aiming to build a shared conceptual space between the human user and the system.

→ Try out STORM, and Co-STORM at storm.genie.stanford.edu