Art or Artifice? LLMs and the False Promise of Creativity (Torrance Test of Creative Writing)
Source: https://arxiv.org/abs/2309.14556
Structured fields
{
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "A 14-test, four-dimension expert rubric for creative writing and the finding that no LLM judge correlated positively with expert ratings; a measured reason to keep critique dimensions separate and human-anchored in the hub's evaluations.",
"source_type": "paper",
"availability": "available",
"source_owner": "Chakrabarty, Laban, Agarwal, Muresan, Wu",
"next_check_at": "2026-11-16T00:00:00.000Z",
"upstream_updated_at": "2024-03-08T00:00:00.000Z"
}Evidence claims
- [upstream_claim] TTCW: 14 binary tests across Fluency, Flexibility, Originality, Elaboration; 10 writers assessed 48 stories; LLM stories passed 3-10x fewer tests; no LLM assessor correlated positively with experts. · locator: abstract source
- [sourced_fact] ACM CHI 2024; CC BY 4.0. · locator: comments and license source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | CC-BY-4.0 | permitted | permitted | permitted | unknown | Paper license. |
Linked records
- Can evaluation keep continuity, composition, lighting intent, camera feasibility, aesthetic preference and narrative purpose as separate dimensions without collapsing into a leaderboard? discusses → this
- What before/after evidence would show that accept/reject exemplars actually reduce corrections on the next scene? discusses → this