---
title: "Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models"
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2402-14207-storm.md
source_license: "arXiv non-exclusive distribution license"
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, Monica S. Lam, Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: AI-for-science'
tags: arxiv, ai-for-science, writing, retrieval, storm
arxiv_id: 2402.14207
alias: 2402-14207-storm
type: pointer
format: pointer
sources:
  - id: S1
    title: "Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models"
    publisher: arXiv
    authors: "Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, Monica S. Lam"
    url: https://arxiv.org/abs/2402.14207
    version_read: "v2 (8 Apr 2024)"
    accessed: 2026-11-12
    license: "arXiv non-exclusive distribution license"
---
# Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models

## Summary
[Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://arxiv.org/abs/2402.14207) (2024) introduces STORM, a system for researching and writing long, organized, grounded articles from scratch, with breadth and structure closer to a Wikipedia page than a short chatbot answer.

What it introduced: a pre-writing stage that discovers several perspectives on a topic, simulates conversations in which those perspectives ask questions of a topic expert grounded in internet sources, and then curates the collected material into an outline before drafting. For evaluation, the authors build FreshWiki from recent high-quality Wikipedia articles and also collect feedback from experienced Wikipedia editors. They report that more STORM articles are judged organized and broad than articles from an outline-driven retrieval baseline, and the editor feedback highlights remaining problems such as source bias and over-association of unrelated facts.

What it led to: a widely discussed research-and-outline pipeline for long-form generation. Live notes: [2005-11401-retrieval-augmented-generation](https://iinventedlight.com/library/notes/2005-11401-retrieval-augmented-generation/). PaperQA2 is a pointer note in this week's batch F.

Where to read it: https://arxiv.org/abs/2402.14207 (v2, last revised 8 Apr 2024). NAACL 2024.

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).
