mlsanityData to 14 Oct 2026

Model Misalignment and Language Change: Traces of AI-Associated Language in Unscripted Spoken English

arXiv 2508.00238 ↗First posted 1 Aug 2025cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

In recent years, written language, particularly in science and education, has undergone remarkable shifts in word usage. These changes are widely attributed to the growing influence of Large Language Models (LLMs), which frequently rely on a distinct lexical style. Divergences between model output and target audience norms can be viewed as a form of misalignment. While these shifts are often linked to using Artificial Intelligence (AI) directly as a tool to generate text, it remains unclear whether the changes reflect broader changes in the human language system itself. To explore this question, we constructed a dataset of 22.1 million words from unscripted spoken language drawn from conversational science and technology podcasts. We analyzed lexical trends before and after ChatGPT's release in 2022, focusing on commonly LLM-associated words. Our results show a moderate yet significant increase in the usage of these words post-2022, suggesting a convergence between human word choices and LLM-associated patterns. In contrast, baseline synonym words exhibit no significant directional shift. Given the short time frame and the number of words affected, this may indicate the onset of a remarkable shift in language use. Whether this represents natural language change or a novel shift driven by AI exposure remains an open question. Similarly, although the shifts may stem from broader adoption patterns, it may also be that upstream training misalignments ultimately contribute to changes in human language use. These findings parallel ethical concerns that misaligned models may shape social and moral beliefs.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 39 of its 84 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

39 of 84 references.

References · 39

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2017Deep reinforcement learning from human preferencescited by 3,912
  4. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  6. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  7. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  8. 2020Aligning AI With Shared Human Valuescited by 723
  9. 2019BLiMP: The Benchmark of Linguistic Minimal Pairs for Englishcited by 564
  10. 2020Artificial Intelligence, Values and Alignmentcited by 448
  11. 2023Can AI-Generated Text be Reliably Detected?cited by 386
  12. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 356
27 more
  1. 2023Self-Consuming Generative Models Go MADcited by 250
  2. 2021Challenges in Detoxifying Language Modelscited by 169
  3. 2023Social Biases through the Text-to-Image Generation Lenscited by 127
  4. 2024Mapping the Increasing Use of LLMs in Scientific Paperscited by 118
  5. 2023Testing of Detection Tools for AI-Generated Textcited by 90
  6. 2023Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loopcited by 79
  7. 2016Research Priorities for Robust and Beneficial Artificial Intelligencecited by 74
  8. 2025MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairscited by 71
  9. 2022Will Large-scale Generative Models Corrupt Future Datasets?cited by 59
  10. 2024Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrievalcited by 51
  11. 2024From Lists to Emojis: How Format Bias Affects Model Alignmentcited by 49
  12. 2024Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challengescited by 47
  13. 2024Empirical evidence of Large Language Model's influence on human spoken communicationcited by 27
  14. 2024ChatGPT "contamination": estimating the prevalence of LLMs in the scholarly literaturecited by 26
  15. 2023Evaluating Biased Attitude Associations of Language Models in an Intersectional Contextcited by 20
  16. 2024The Impact of Large Language Models in Academia: from Writing to Speakingcited by 18
  17. 2023Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articlescited by 16
  18. 2024Towards the relationship between AIGC in manuscript writing and author profiles: evidence from preprints in LLMscited by 14
  19. 2023Evaluating the Fairness of Discriminative Foundation Models in Computer Visioncited by 12
  20. 2024How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studiescited by 10
  21. 2025Linguistic Generalizations are not Rules: Impacts on Evaluation of LMscited by 10
  22. 2018The Dynamics of Norm Change in the Cultural Evolution of Languagecited by 8
  23. 2023Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluationcited by 8
  24. 2024On the Pros and Cons of Active Learning for Moral Preference Elicitationcited by 7
  25. 2025Examining Linguistic Shifts in Academic Writing Before and After the Launch of ChatGPT: A Study on Preprint Paperscited by 6
  26. 2025TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documentscited by 6
  27. 2024Syntactic Language Change in English and German: Metrics, Parsers, and Convergencescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writingcited by 2
  2. 2026Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learningcited by 0
  3. 2026Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Modelscited by 0
  4. 2026Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognitioncited by 0