Metraipolis › archive › dc_704e2edbeeae

Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition — arXiv:2611.01284

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01284
License (as archived): CC0-1.0
Archived: 2026-11-03T18:17:49.293Z
SHA-256 of the archived text: 1617fc272e4bff3fcbd2d2a5f2d798028c39c4e46ff0732ce678b146a4e3d182
Stable URL of this page: https://metraipolis.com/documento/dc_704e2edbeeae

How to cite

Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition — arXiv:2611.01284 — arXiv (en), https://arxiv.org/abs/2611.01284 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_704e2edbeeae (Metraipolis archive dc_704e2edbeeae, sha256 1617fc272e4bff3fcbd2d2a5f2d798028c39c4e46ff0732ce678b146a4e3d182)

BibTeX

@misc{dc704e2edbeeae,
  title = {Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition — arXiv:2611.01284},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01284},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_704e2edbeeae; sha256 1617fc272e4bff3fcbd2d2a5f2d798028c39c4e46ff0732ce678b146a4e3d182},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01284. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Character names in large language model (LLM) fiction concentrate on a handful of recurrent names such as 'Elara' and 'Elias', a measurable face of AI slop. Existing fixes either require logit access or retraining, or operate per request and cannot control concentration across a corpus. How much prompt-level strategies reduce concentration, and at what cost to name naturalness, has not been systematically measured. We present an empirical study of name-concentration control across eight strategies and introduce speculative naming, a fine-tuning-free method that adapts the draft-verify-reject paradigm of speculative decoding from tokens to names. The method requests candidate name-sets through verbalized sampling, scores them against a SlopTracker that combines a per-model fingerprint with a runtime counter, and selects through a temperature-controlled rule or its strict variant (HARD). We use 20 LLMs to generate 44,782 stories in four languages from text and visual stimuli (88,919 named characters), and measure concentration with a list-free collision metric (Slop Ratio, SR) decomposed into known and emergent components. List-based strategies do not remove slop: static banlists displace concentration to emergent names and more than halve the share of attested real names. Speculative naming removes it: the sampling scaffold alone cuts SR by 89% on average, the dynamic tracker brings the total reduction to 95%, mean collision probability falls from 7.3% to 0.4%, and known-name collisions hold at zero while naturalness stays close to baseline (42-69% attested by language) and within-story collisions drop from 4.3% to 0.2%. The strategy ranking is stable across languages, model families, and name-counting conventions. Name concentration is thus controllable at the corpus level without logit access or retraining; broader creative diversity beyond naming remains open.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01284 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:09:53.577Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).