What do later open studies measure about LLM NPC dialogue in games (player ratings, grounding errors, prompt scaffolding), and how small or weak is the evidence for production writing?

Two open studies were read in full-text excerpt form. Akoury et al. (Findings of EMNLP 2023) had 28 players compare GPT-4 infilled lines against Disco Elysium writers' lines and found designer prose preferred, with 32% of rated generations illogical in context. Figueiredo and Elumeze (arXiv 2510.25820v1) ran a 10-person usability study (no reliable difference after correction) plus a gpt-4o-judged synthetic probe of 60 scripted interactions in which scaffolding helped a quest-giver and hurt suspect NPCs. Both are small, single-game, short-horizon studies; neither measures lore consistency over long play. Curator qualifications: All excerpts located; Park (beats crowdworkers) vs Akoury (designer prose preferred to GPT-4) - different baselines, kept. Disco Elysium text terms remain a rights hold (FB43). Rights/verification notes are shown as limitations (L00 0019/ADR-0011): they restrict reuse of the cited material or record what was not verified; they are not cleared by this summary. Limitations: [component_reuse_restriction] Disco Elysium game-text terms uninspected (hold). Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://aclanthology.org/2023.findings-emnlp.151.pdf",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/html/2510.25820v1",
      "note": "candidate evidence excerpts"
    }
  ]
}