Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models

• URL: http://arxiv.org/abs/2606.03165v1
• Date: Tue, 02 Jun 2026 05:23:45 GMT
• Title: Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models
• Abstract summary: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment)<n>This paper introduces two curation-free, assumption-light evaluation metrics: the Lexical Alignment Score and the Triangulated Preference Shift.<n>The procedure identifies, without manual intervention, overused items such as'suggest', 'additionally', and'strategy', and estimates their link to preference learning.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment). Research, mostly on Scientific English, has described both what divergences occur and, to some extent, why, linking them to the training stage of human preference learning. Yet, existing approaches rely on manual curation. This paper introduces two curation-free, assumption-light evaluation metrics: the Lexical Alignment Score, which identifies lexical overuse, and the Triangulated Preference Shift, which quantifies how much of such shifts can be attributed to human preference learning. Using PubMed abstracts, continuations were generated and measured using windowed document prevalence across six model families (Falcon, Gemma, Llama, Mistral, OLMo, Yi). The procedure identifies, without manual intervention, overused items such as 'suggest', 'additionally', and 'strategy', and estimates their link to preference learning. Our findings replicate prior work and remain stable across parameter settings, random seeds, and evaluation on further data. The approach scales readily and enables systematic study of lexical (mis)alignment beyond Scientific English and across languages, and as such, the metrics have the potential to contribute to improved alignment for future models and understanding of its origins.

Related papers

• Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning [0.33463386076921503]
  We introduce the Triangulated Preference Shift score, a metric that triangulates between human gold standards, base models, and variants.<n>We provide data across six model families, anchor the results in the literature, and illustrate the general approach's utility.
  arXiv  Detail & Related papers  (2026-05-29T20:19:49Z)
• A Distributional Perspective on Word Learning in Neural Language Models [57.41607944290822]
  There are no widely agreed-upon metrics for word learning in language models.<n>We argue that distributional signatures studied in prior work fail to capture key distributional information.<n>We obtain learning trajectories for a selection of small language models we train from scratch.
  arXiv  Detail & Related papers  (2025-02-09T13:15:59Z)
• Reverse-Engineering the Reader [43.26660964074272]
  We introduce a novel alignment technique in which we fine-tune a language model to implicitly optimize the parameters of a linear regressor. Using words as a test case, we evaluate our technique across multiple model sizes and datasets. We find an inverse relationship between psychometric power and a model's performance on downstream NLP tasks as well as its perplexity on held-out test data.
  arXiv  Detail & Related papers  (2024-10-16T23:05:01Z)
• Locally Measuring Cross-lingual Lexical Alignment: A Domain and Word Level Perspective [15.221506468189345]
  We present a methodology for analyzing both synthetic validations and a novel naturalistic validation using lexical gaps in the kinship domain. Our analysis spans 16 diverse languages, demonstrating that there is substantial room for improvement with the use of newer language models.
  arXiv  Detail & Related papers  (2024-10-07T16:37:32Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Semantic Coherence Markers for the Early Diagnosis of the Alzheimer Disease [0.0]
  Perplexity was originally conceived as an information-theoretic measure to assess how much a given language model is suited to predict a text sequence. We employed language models as diverse as N-grams, from 2-grams to 5-grams, and GPT-2, a transformer-based language model. Best performing models achieved full accuracy and F-score (1.00 in both precision/specificity and recall/sensitivity) in categorizing subjects from both the AD class and control subjects.
  arXiv  Detail & Related papers  (2023-02-02T11:40:16Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• Detecting Text Formality: A Study of Text Classification Approaches [78.11745751651708]
  This work proposes the first to our knowledge systematic study of formality detection methods based on statistical, neural-based, and Transformer-based machine learning methods. We conducted three types of experiments -- monolingual, multilingual, and cross-lingual. The study shows the overcome of Char BiLSTM model over Transformer-based ones for the monolingual and multilingual formality classification task.
  arXiv  Detail & Related papers  (2022-04-19T16:23:07Z)
• A Latent-Variable Model for Intrinsic Probing [93.62808331764072]
  We propose a novel latent-variable formulation for constructing intrinsic probes.<n>We find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
  arXiv  Detail & Related papers  (2022-01-20T15:01:12Z)
• 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)

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.