LLM 写小说爱用 Elara？论文用投机命名法把名字重复率降 95%
Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition
写 AI 小说全是一个名字的可以看看，不用重训模型，改一下采样流程就能把角色名重复砍掉 95%，还给了 20 个模型的实测数据。
arXiv 论文发现 20 个 LLM 生成的 44,782 篇故事中，角色名集中在 Elara、Elias 等少数高频名字上。作者对比八种策略，发现静态 banlist 只是把重复转移到其他名字上。论文提出的投机命名法不需要 logit 访问或重新训练，先通过 verbalized sampling 获取候选名字集，再用 SlopTracker 按 Slop Ratio 指标打分筛选。该方法把平均 Slop Ratio 降低 95%，名字碰撞概率从 7.3% 降到 0.4%，故事内重名率从 4.3% 降到 0.2%，名字自然度接近基线水平。
Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition
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.