{"slug": "character-name-concentration-in-llm-fiction-measuring-displacement-and", "title": "Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition", "summary": "A study of 20 large language models generating 44,782 stories in four languages found that a fine-tuning-free method called speculative naming cut character-name concentration by 95% on average, according to the arXiv paper 2611.01284v1. The sampling scaffold alone reduced the Slop Ratio by 89%, and adding a dynamic SlopTracker brought the total reduction to 95%, lowering mean collision probability from 7.3% to 0.4% and within-story collisions from 4.3% to 0.2% across 88,919 named characters. The authors report that static banlists do not remove the concentration on names such as 'Elara' and 'Elias' but displace it to emergent names and more than halve the share of attested real names, while speculative naming holds known-name collisions at zero with naturalness at 42-69% attested by language.", "body_md": "arXiv:2611.01284v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/character-name-concentration-in-llm-fiction-measuring-displacement-and", "canonical_source": "https://www.machinebrief.com/news/character-name-concentration-in-llm-fiction-measuring-displa-fd5k", "published_at": "2026-11-04 05:00:00+00:00", "updated_at": "2026-11-04 07:21:11.808573+00:00", "lang": "en", "topics": ["large-language-models", "generative-ai", "ai-research", "artificial-intelligence"], "entities": ["Elara", "Elias", "SlopTracker", "Slop Ratio", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/character-name-concentration-in-llm-fiction-measuring-displacement-and", "markdown": "https://wpnews.pro/news/character-name-concentration-in-llm-fiction-measuring-displacement-and.md", "text": "https://wpnews.pro/news/character-name-concentration-in-llm-fiction-measuring-displacement-and.txt", "jsonld": "https://wpnews.pro/news/character-name-concentration-in-llm-fiction-measuring-displacement-and.jsonld"}}