How does Re3 generate a 2,000-word story automatically, and what did its human evaluation and ablations show?

Partially verified: the curator re-read none of the cited sources; S2 rests on the producer's pinned reading. Re3 (Yang et al., EMNLP 2022) has four modules: Plan (setting, characters, three-point outline via GPT3-Instruct-175B), Draft (recursively rebuilt prompt from relevant plan items, summaries and the last passage, GPT3-175B), Rewrite (rerank continuations with trained coherence and relevance classifiers plus heuristics) and Edit (character attribute contradiction detection and correction). Against GPT-3 rolling-window baselines, MTurk raters judged 14.3 and 20.0 points more Re3 stories coherent and premise-relevant; ablations show Plan and Rewrite matter and Edit does not; inter-annotator agreement was low. Curator qualifications: Partially verified: the curator re-read none of the cited sources; S2 rests on the producer's pinned reading. Curator GET 2026-10-23 of the sources not re-read (mechanical source evidence, not semantic verification): S2: HTTP 200, bytes differ from the producer pin. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://arxiv.org/abs/2210.06774v3",
      "note": "candidate evidence excerpts"
    }
  ]
}