Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)

• URL: http://arxiv.org/abs/2605.27268v1
• Date: Tue, 26 May 2026 16:44:25 GMT
• Title: Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)
• Abstract summary: We introduce the Word Coverage Score (WCS), a metric that quantifies the extent to which contextually appropriate human vocabulary is mathematically pruned by standard sampling filters.<n>By auditing open-weight models on human-authored corpus fragments, we identify which logical lexical choices are rendered unreachable by the decoder.
• Score: 3.71430272682278
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern Large Language Models (LLMs) are often criticized for producing repetitive and homogeneous text, despite possessing vast latent vocabularies. While previous research has focused on model knowledge and training data, we investigate the role of decoding mechanics in suppressing linguistic diversity. We introduce the Word Coverage Score (WCS), a metric that quantifies the extent to which contextually appropriate human vocabulary is mathematically pruned by standard sampling filters (e.g., Top-$p$, Top-$k$, and Min-$p$). Rather than assessing static knowledge, the WCS measures the lexical survival rate of low-frequency, high-information human words as a function of sampling parameters. By auditing open-weight models on human-authored corpus fragments, we identify which logical lexical choices are rendered unreachable by the decoder, even when they reside within the probability space. Our results provide quantitative evidence that industry-standard sampling defaults act as unintended censorship mechanisms, smoothing the unique textures of human expression into a homogenized discourse. The WCS offers a rigorous framework for optimizing the trade-off between text coherence and lexical richness, providing a diagnostic tool for preserving the diversity of human language in generative models.

Related papers

• WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribute Classification [2.634639188510826]
  We propose a human-large language model (LLM) collaborative re-annotation framework for stabilizing multilingual speaker-attribute labels.<n>Using this framework, we construct WhoSaidIt, a multilingual dataset covering nine speaker-attribute labels.
  arXiv  Detail & Related papers  (2026-05-25T17:37:45Z)
• How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework [0.47954782871066737]
  We propose a context-aware evaluation framework in which human-likeness is assessed.<n>We implement this framework using the Maximum Mean Discrepancy (MMD) and the 67 lexico-grammatical features introduced by Biber.
  arXiv  Detail & Related papers  (2026-05-22T14:04:25Z)
• WESR: Scaling and Evaluating Word-level Event-Speech Recognition [59.21814194620928]
  Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying.<n>We develop a refined taxonomy of 21 vocal events, with a new categorization into discrete (standalone) versus continuous (mixed with speech) types.<n>Based on the refined taxonomy, we introduce WESR-Bench, an expert-annotated evaluation set (900+ utterances) with a novel position-aware protocol.
  arXiv  Detail & Related papers  (2026-01-08T02:23:21Z)
• Computational Turing Test Reveals Systematic Differences Between Human and AI Language [0.0]
  Large language models (LLMs) are increasingly used in the social sciences to simulate human behavior.<n>Existing validation efforts rely heavily on human-judgment-based evaluations.<n>This paper introduces a computational Turing test to assess how closely LLMs approximate human language.
  arXiv  Detail & Related papers  (2025-11-06T08:56:37Z)
• Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks [7.216732751280017]
  We correlate Tokenization Parity (TP) and Information Parity (IP) as measures of representational biases in pre-trained multilingual models.<n>We compare state-of-the-art decoder-only LLMs with encoder-based models across three tasks: dialect classification, topic classification, and extractive question answering.<n>Our analysis reveals that TP is a better predictor of the performance on tasks reliant on syntactic and morphological cues, while IP better predicts performance in semantic tasks.
  arXiv  Detail & Related papers  (2025-09-24T12:13:53Z)
• Generative Spoken Language Model based on continuous word-sized audio tokens [52.081868603603844]
  We introduce a Generative Spoken Language Model based on word-size continuous-valued audio embeddings. The resulting model is the first generative language model based on word-size continuous embeddings.
  arXiv  Detail & Related papers  (2023-10-08T16:46:14Z)
• Language Model Decoding as Direct Metrics Optimization [87.68281625776282]
  Current decoding methods struggle to generate texts that align with human texts across different aspects. In this work, we frame decoding from a language model as an optimization problem with the goal of strictly matching the expected performance with human texts. We prove that this induced distribution is guaranteed to improve the perplexity on human texts, which suggests a better approximation to the underlying distribution of human texts.
  arXiv  Detail & Related papers  (2023-10-02T09:35:27Z)
• Locally Typical Sampling [84.62530743899025]
  We show that today's probabilistic language generators fall short when it comes to producing coherent and fluent text.<n>We propose a simple and efficient procedure for enforcing this criterion when generating from probabilistic models.
  arXiv  Detail & Related papers  (2022-02-01T18:58:45Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing [73.16475763422446]
  We propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) It incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness.
  arXiv  Detail & Related papers  (2021-03-21T17:20:38Z)
• Analysis and Evaluation of Language Models for Word Sense Disambiguation [18.001457030065712]
  Transformer-based language models have taken many fields in NLP by storm. BERT can accurately capture high-level sense distinctions, even when a limited number of examples is available for each word sense. BERT and its derivatives dominate most of the existing evaluation benchmarks.
  arXiv  Detail & Related papers  (2020-08-26T15:07:07Z)

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.