韩语论文摘要中出现大量新词汇，疑似受大模型影响。
An LLM-Associated Register Shift in Korean Journal Abstracts: A Morphology-Aware Excess-Vocabulary Study, 2018-2026
- 用形态学单位分析39万篇韩语论文摘要，发现2024年后词汇使用异常增长
- 2026年'建议'类词使用率达21.4%，远超预期的5.3%；动词使用量下降四分之一
- 即使排除翻译、领域等因素，仍可见显著变化，适合关注AI对学术语言影响的研究者
本文将过度词汇（超过2023年前趋势的词频）概念引入韩语学术摘要，基于398,296篇韩国科学引文索引（KCI）摘要（2018–2026年8月）进行研究，并以47,165篇越南语摘要为对照。随机基准测试显示，单字统计误差在0.1–2.2点之间，分半重选统计最多2.9点。韩语摘要在2023年无异常，2024年末开始显现，2025年持续上升，2026年中趋于平稳：'suggest'（sisahada）在2026年出现在21.4%的摘要中，远高于预期的5.3%；普通动词如'look into'（araboda）使用率降至趋势值的四分之一。在假设条件下，大模型处理摘要的单字条件置信下限分别为2024–2026年的3.5%、10.5%、16.1%；分半集下限为7.8%、20.6%、33.0%。同类学科中Holzwarth等人估算结果为2025–2026年的41.9%和72.1%。控制主题后异常仍存在：仅保留三名语言模型标注器一致视为‘风格’的词元，仍保留33.0点中的14.7点；将每篇2026年摘要与同期刊基期摘要配对后，仍残留34.1点。翻译路径无法解释该现象：韩语表面标记上升时，其译文特征反而下降。同一文章的英文摘要中，过度词汇提前一年出现；当英文无异常时，韩语异常仍维持在30%–66%的强度。三家机构提供的对照摘要同样呈现词汇上升趋势，标记更替与模型版本演进一致；隐含流行度具有情境依赖性。
原文摘要 · Abstract (English)
Excess vocabulary, a word's frequency above its pre-2023 trend, is how the change in scholarly English after 2022 has been measured. We adapt it to Korean with morphological units on 398,296 KCI abstracts (2018-August 2026), with 47,165 Vietnamese abstracts for comparison. Placebo floors are 0.1-2.2 points for the single-word statistic and at most 2.9 for the re-selected split-half set statistic. Korean abstracts show nothing in 2023, onset in late 2024, a rise through 2025 flattening in mid-2026: sisahada "suggest" appears in 21.4% of 2026 abstracts against 5.3% expected; plain verbs like araboda "look into" fall to a quarter of trend. Under stated assumptions the single-word conditional lower bound on LLM-processed abstracts is 3.5%, 10.5% and 16.1% for 2024-2026 and a split-half set bound 7.8%, 20.6% and 33.0%. Holzwarth et al.'s estimator under the same discipline gives 41.9% and 72.1% for 2025-2026. Subject-matter controls reduce but do not remove it: restricting the set to lemmas three language-model annotators all call style leaves 14.7 of the 33.0 points, and pairing each 2026 abstract with its journal's closest base-period abstract leaves 34.1. Tested translation routes do not explain it: the surface marks of translated Korean fall as the markers rise. In the same articles' English abstracts the excess appears a year earlier; where the English side carries none, the Korean shift persists at 30 to 66% of the rate where it does. Control abstracts from three providers reproduce the rising words, with marker turnover consistent with model generations; implied prevalences are scenario-dependent.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。