HANNA: benchmark for evaluating automatic story generation (Chhun et al.)

{
  "checked_at": "2026-10-17T00:00:00.000Z",
  "usefulness": "Defines 6 human story-quality criteria and releases 1,056 human-annotated stories from 10 systems; the base for judging whether automatic metrics correlate with human story judgments.",
  "source_type": "paper",
  "availability": "available",
  "source_owner": "Chhun, Colombo, Suchanek, Clavel",
  "next_check_at": "2026-10-24T00:00:00.000Z",
  "known_limitations": [
    "Stories are short and pre-date current LLMs."
  ]
}