Scaling Self-Supervised Speech Models Uncovers Deep Linguistic Relationships: Evidence from the Pacific Cluster

• URL: http://arxiv.org/abs/2603.07238v1
• Date: Sat, 07 Mar 2026 14:48:48 GMT
• Title: Scaling Self-Supervised Speech Models Uncovers Deep Linguistic Relationships: Evidence from the Pacific Cluster
• Abstract summary: Similarities between language representations derived from Self-Supervised Speech Models (S3Ms) have been observed to primarily reflect geographic proximity or surface typological similarities driven by recent expansion or contact.<n>We investigate how scaling linguistic coverage of an S3M-based language identification system from 126 to 4,017 languages influences this topology.
• Score: 23.057593480189652
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Similarities between language representations derived from Self-Supervised Speech Models (S3Ms) have been observed to primarily reflect geographic proximity or surface typological similarities driven by recent expansion or contact, potentially missing deeper genealogical signals. We investigate how scaling linguistic coverage of an S3M-based language identification system from 126 to 4,017 languages influences this topology. Our results reveal a non-linear effect: while phylogenetic recovery remains stagnant up to the 1K scale, the 4K model displays a dramatic qualitative shift, resolving both clear lineages and complex, long-term linguistic contact. Notably, our analysis reveals the emergence of a robust macro-cluster in the Pacific (comprising Papuan, Oceanic, and Australian languages) and investigates its latent drivers. We find that the 4K model utilizes a more concentrated encoding that captures shared, robust acoustic signatures such as global energy dynamics. These findings suggest that massive S3Ms can internalize multiple layers of language history, providing a promising perspective for computational phylogenetics and the study of language contact.

Related papers

• The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models [12.320824168302908]
  We present a systematic analysis of the verbal tic phenomenon across eight state-of-the-art Large Language Models (LLMs)<n>We introduce the Verbal Tic Index (VTI), a composite metric quantifying tic prevalence, and analyze its correlation with sycophancy, lexical diversity, and human-perceived naturalness.
  arXiv  Detail & Related papers  (2026-04-21T06:43:01Z)
• Phonological distances for linguistic typology and the origin of Indo-European languages [0.0]
  We show that short-range phoneme dependencies encode large-scale patterns of linguistic relatedness.<n>Using an information-theoretic framework, we argue that phoneme sequences modeled as second-order Markov chains essentially capture the statistical correlations of a phonological system.
  arXiv  Detail & Related papers  (2026-04-13T14:48:15Z)
• Investigating the Influence of Language on Sycophantic Behavior of Multilingual LLMs [1.7778609937758327]
  Large language models (LLMs) have achieved strong performance across a wide range of tasks, but they are also prone to sycophancy.<n>Previous research has outlined both the extent and the underlying causes of sycophancy in earlier models, such as ChatGPT-3.5 and Davinci.<n>This work investigates how the language influences sycophantic responses.
  arXiv  Detail & Related papers  (2026-03-29T12:31:05Z)
• Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG [21.253523606290685]
  We examine layer-wise representational alignment between 12 open-source Audio LLMs and Electroencephalogram (EEG) signals across 2 datasets.<n>Our analysis reveals 3 key findings: (1) we observe a rank-related split, in which model rankings vary substantially across different similarity metrics; (2) we identify-temporal alignment patterns characterized by depth-dependent alignment peaks and a pronounced increase in RSA within the 250-500 ms time window, consistent with N400 neural dynamics; and (3) we find an affective whereby negativeody capabilities, identified using a proposed Trimodal- Consistency Neighborhood (TNC) criterion, reduces geometric similarity dependence while enhancing
  arXiv  Detail & Related papers  (2026-01-23T08:18:29Z)
• The Emergence of Abstract Thought in Large Language Models Beyond Any Language [95.50197866832772]
  Large language models (LLMs) function effectively across a diverse range of languages.<n>Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts.<n>Recent results show strong multilingual performance, even surpassing English performance on specific tasks in other languages.
  arXiv  Detail & Related papers  (2025-06-11T16:00:54Z)
• Neighbors and relatives: How do speech embeddings reflect linguistic connections across the world? [0.7168794329741259]
  This study employs embeddings from the fine-tuned XLS-R self-supervised language identification model vox107-xls-r-300m-wav2vec to analyze relationships between 106 world languages.<n>Using linear discriminant analysis (LDA), language embeddings are clustered and compared with genealogical, lexical, and geographical distances.<n>The results demonstrate that embedding-based distances align closely with traditional measures, effectively capturing both global and local typological patterns.
  arXiv  Detail & Related papers  (2025-06-10T08:33:34Z)
• Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models [56.61984030508691]
  We present the first mechanistic interpretability study of language confusion.<n>We show that confusion points (CPs) are central to this phenomenon.<n>We show that editing a small set of critical neurons, identified via comparative analysis with a multilingual-tuned counterpart, substantially mitigates confusion.
  arXiv  Detail & Related papers  (2025-05-22T11:29:17Z)
• Analysis of Argument Structure Constructions in a Deep Recurrent Language Model [0.0]
  We explore the representation and processing of Argument Structure Constructions (ASCs) in a recurrent neural language model. Our results show that sentence representations form distinct clusters corresponding to the four ASCs across all hidden layers. This indicates that even a relatively simple, brain-constrained recurrent neural network can effectively differentiate between various construction types.
  arXiv  Detail & Related papers  (2024-08-06T09:27:41Z)
• Holmes: A Benchmark to Assess the Linguistic Competence of Language Models [59.627729608055006]
  We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence. We use computation-based probing to examine LMs' internal representations regarding distinct linguistic phenomena. As a result, we meet recent calls to disentangle LMs' linguistic competence from other cognitive abilities.
  arXiv  Detail & Related papers  (2024-04-29T17:58:36Z)
• MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models [44.74364661212373]
  This paper proposes MulCogBench, a cognitive benchmark dataset collected from native Chinese and English participants. It encompasses a variety of cognitive data, including subjective semantic ratings, eye-tracking, functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG) Results show that language models share significant similarities with human cognitive data and the similarity patterns are modulated by the data modality and stimuli complexity.
  arXiv  Detail & Related papers  (2024-03-02T07:49:57Z)
• Patterns of Persistence and Diffusibility across the World's Languages [3.7055269158186874]
  Colexification is a type of similarity where a single lexical form is used to convey multiple meanings. We shed light on the linguistic causes of cross-lingual similarity in colexification and phonology. We construct large-scale graphs incorporating semantic, genealogical, phonological and geographical data for 1,966 languages.
  arXiv  Detail & Related papers  (2024-01-03T12:05:38Z)
• Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects [82.81964713263483]
  A popular approach to decompose the neural bases of language consists in correlating, across individuals, the brain responses to different stimuli. Here, we show that a model-based approach can reach equivalent results within subjects exposed to natural stimuli.
  arXiv  Detail & Related papers  (2021-10-12T15:30:21Z)
• A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space [61.18554842370824]
  In cross-lingual language models, representations for many different languages live in the same space. We compute a task-based measure of cross-lingual alignment in the form of bitext retrieval performance. We examine a range of linguistic, quasi-linguistic, and training-related features as potential predictors of these alignment metrics.
  arXiv  Detail & Related papers  (2021-09-13T21:05:37Z)
• Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures [73.06435180872293]
  We construct a recurrent neural network predictor based on byte embeddings and convolutional layers. We show that some features from various linguistic types can be predicted reliably.
  arXiv  Detail & Related papers  (2020-04-30T21:00:53Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.