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

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

URL: http://arxiv.org/abs/2508.00238v1
Date: Fri, 01 Aug 2025 00:47:33 GMT
Title: Model Misalignment and Language Change: Traces of AI-Associated Language in Unscripted Spoken English
Authors: Bryce Anderson, Riley Galpin, Tom S. Juzek,
Abstract summary: In recent years, written language, particularly in science and education, has undergone remarkable shifts in word usage.<n> Divergences between model output and target audience norms can be viewed as a form of misalignment.<n>We constructed a dataset of 22.1 million words from unscripted spoken language drawn from conversational science and technology podcasts.
Score: 0.0
License: http://creativecommons.org/licenses/by-sa/4.0/
Abstract: 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.

Related papers

Exploring the Structure of AI-Induced Language Change in Scientific English [0.0]
We find that entire semantic clusters often shift together, with most or all words in a group increasing in usage.<n>This pattern suggests that changes induced by Large Language Models are primarily semantic and pragmatic rather than purely lexical.<n>Our analysis of "collapsing" words reveals a more complex picture, which is consistent with organic language change.
arXiv Detail & Related papers (2025-06-26T23:44:24Z)
Can Language Models Learn Typologically Implausible Languages? [62.823015163987996]
Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans.<n>We discuss how language models (LMs) allow us to better determine the role of domain-general learning biases in language universals.<n>We test LMs on an array of highly naturalistic but counterfactual versions of the English (head-initial) and Japanese (head-final) languages.
arXiv Detail & Related papers (2025-02-17T20:40:01Z)
We're Calling an Intervention: Exploring Fundamental Hurdles in Adapting Language Models to Nonstandard Text [8.956635443376527]
We present a suite of experiments that allow us to understand the underlying challenges of language model adaptation to nonstandard text.<n>We do so by designing interventions that approximate core features of user-generated text and their interactions with existing biases of language models.<n>Applying our interventions during language model adaptation to nonstandard text variations, we gain important insights into when such adaptation is successful.
arXiv Detail & Related papers (2024-04-10T18:56:53Z)
Syntactic Language Change in English and German: Metrics, Parsers, and Convergences [56.47832275431858]
The current paper looks at diachronic trends in syntactic language change in both English and German, using corpora of parliamentary debates from the last c. 160 years. We base our observations on five dependencys, including the widely used Stanford Core as well as 4 newer alternatives. We show that changes in syntactic measures seem to be more frequent at the tails of sentence length distributions.
arXiv Detail & Related papers (2024-02-18T11:46:16Z)
Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
arXiv Detail & Related papers (2022-10-14T02:35:19Z)
Do Not Fire the Linguist: Grammatical Profiles Help Language Models Detect Semantic Change [6.7485485663645495]
We first compare the performance of grammatical profiles against that of a multilingual neural language model (XLM-R) on 10 datasets, covering 7 languages. Our results show that ensembling grammatical profiles with XLM-R improves semantic change detection performance for most datasets and languages.
arXiv Detail & Related papers (2022-04-12T11:20:42Z)
Towards Zero-shot Language Modeling [90.80124496312274]
We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
arXiv Detail & Related papers (2021-08-06T23:49:18Z)
How individuals change language [1.2437226707039446]
We introduce a very general mathematical model that encompasses a wide variety of individual-level linguistic behaviours. We compare the likelihood of empirically-attested changes in definite and indefinite articles in multiple languages under different assumptions. We find that accounts of language change that appeal primarily to errors in childhood language acquisition are very weakly supported by the historical data.
arXiv Detail & Related papers (2021-04-20T19:02:49Z)
Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks [58.87961226278285]
We propose a self-supervised approach to model lexical semantic change. We show that our method can be used for the detection of semantic change with any alignment method. We illustrate the utility of our techniques using experimental results on three different datasets.
arXiv Detail & Related papers (2021-01-30T18:59:43Z)
Lexical semantic change for Ancient Greek and Latin [61.69697586178796]
Associating a word's correct meaning in its historical context is a central challenge in diachronic research. We build on a recent computational approach to semantic change based on a dynamic Bayesian mixture model. We provide a systematic comparison of dynamic Bayesian mixture models for semantic change with state-of-the-art embedding-based models.
arXiv Detail & Related papers (2021-01-22T12:04:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.