we propose the STORM paradigm for the Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking
oh come the fuck on
The authors hail from Monica S. Lam's group at Stanford, which has also published several other papers involving LLMs and Wikimedia projects since 2023 (see our previous coverage: WikiChat, "the first few-shot LLM-based chatbot that almost never hallucinates" – a paper that received the Wikimedia Foundation's "Research Award of the Year" some weeks ago).
from the same minds as STOTRMPQA comes: we constructed this LLM so it won’t generate a response unless similar text appears in the Wikipedia corpus and now it almost never entirely fucks up. award-winning!