Hierarchical Geometry of Cognitive States in Transformer Embedding Spaces

• URL: http://arxiv.org/abs/2512.22227v1
• Date: Tue, 23 Dec 2025 03:37:34 GMT
• Title: Hierarchical Geometry of Cognitive States in Transformer Embedding Spaces
• Abstract summary: We investigate whether sentence embeddings encode a graded, hierarchical structure aligned with human-interpretable cognitive or psychological attributes.<n>We construct a dataset of 480 natural-language sentences annotated with continuous ordinal energy scores and discrete tier labels.<n>Across models, both continuous scores and tier labels are reliably decodable, with shallow nonlinear probes providing consistent performance gains.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work has shown that transformer-based language models learn rich geometric structure in their embedding spaces, yet the presence of higher-level cognitive organization within these representations remains underexplored. In this work, we investigate whether sentence embeddings encode a graded, hierarchical structure aligned with human-interpretable cognitive or psychological attributes. We construct a dataset of 480 natural-language sentences annotated with continuous ordinal energy scores and discrete tier labels spanning seven ordered cognitive categories. Using fixed sentence embeddings from multiple transformer models, we evaluate the recoverability of these annotations via linear and shallow nonlinear probes. Across models, both continuous scores and tier labels are reliably decodable, with shallow nonlinear probes providing consistent performance gains over linear probes. Lexical TF-IDF baselines perform substantially worse, indicating that the observed structure is not attributable to surface word statistics alone. Nonparametric permutation tests further confirm that probe performance exceeds chance under label-randomization nulls. Qualitative analyses using UMAP visualizations and confusion matrices reveal smooth low-to-high gradients and predominantly adjacent-tier confusions in embedding space. Taken together, these results provide evidence that transformer embedding spaces exhibit a hierarchical geometric organization aligned with human-defined cognitive attributes, while remaining agnostic to claims of internal awareness or phenomenology.

Related papers

• Curved Inference II: Sleeper Agent Geometry - Extending Interpretability Beyond Probes [0.0]
  This paper extends Anthropic's Sleeper Agents research, which showed artificial backdoors persist through safety training & can be detected by linear probes with >99% accuracy.<n>We introduce a naturalistic methodology using multi-turn context windows that simulates realistic deceptive reasoning without artificial triggers or supervised backdoor insertion.<n> Geometric structure reliably predicts semantic classification, with statistically significant differences in surface area across five prompt strategies & two model families.
  arXiv  Detail & Related papers  (2026-08-25T03:51:20Z)
• Convergent Evolution in Neural Representation Space: Emergent Order in Deep Belief Networks [2.925652638976278]
  Deep Belief Networks (DBNs) learn hierarchical generative models without class supervision.<n>We analyze successive layers of DBNs trained on MNIST, Fashion-MNIST, and KMNIST.<n>We find that class-specific clustering generally increases with depth across datasets and network widths.
  arXiv  Detail & Related papers  (2026-08-06T13:05:37Z)
• Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents [0.0]
  This paper introduces Lexical Consensus, an experimental framework for studying grounded word learning over a structured perceptual substrate.<n>We test whether agents can acquire artificial labels for visual concepts, generalize them bidirectionally, and stabilize them across controlled settings.<n>The main result is a robust perceptual-coherence gradient: native categories are easiest to learn, coherent overextensions remain learnable, mid-range disjunctive concepts degrade, and far-disjunctive concepts approach chance.
  arXiv  Detail & Related papers  (2026-06-20T20:08:07Z)
• Online Continual Learning with Dynamic Label Hierarchies [72.33335166136045]
  We introduce a new problem setting, DHOCL, where severity evolve across granularities and each sample provides supervision at a single hierarchical level.<n>In this setting, we find two fundamental issues: (i) partial supervision under mixed granularities provides only point-wise signals over an evolving path-wise hierarchy, which constrains plasticity and undermines cross-level semantic consistency.<n>We propose HALO, which adaptively combines complementary classification heads, regularized by organized learnable hierarchical prototypes, enabling rapid adaptation, hierarchical consistency, and structured knowledge consolidation as the taxonomy evolves.
  arXiv  Detail & Related papers  (2026-05-12T08:20:23Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy [0.8665758002017515]
  This study investigates the internal neural representations of cognitive complexity using Bloom's taxonomy as a hierarchical lens.<n>We probe whether different cognitive levels, ranging from basic recall (Remember) to abstract synthesis (Create) are linearly separable within the model's residual streams.
  arXiv  Detail & Related papers  (2026-02-19T10:19:04Z)
• The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI [0.0]
  This paper introduces a novel auditing framework to quantify latent trait estimation under ordinal uncertainty.<n>The research audits nine leading models across dimensions including Optimization Bias, Sycophancy, and Status-Quo Legitimization.
  arXiv  Detail & Related papers  (2026-02-19T06:56:01Z)
• Generalization Gaps in Political Fake News Detection: An Empirical Study on the LIAR Dataset [0.764671395172401]
  We present a diagnostic evaluation of nine machine learning algorithms on the LIAR benchmark.<n>We uncover a hard "Performance Ceiling", with fine-grained classification not exceeding a weighted F1-score of 0.32 across models.<n>A massive "Generalization Gap" in tree-based ensembles, which achieve more than 99% training accuracy but collapse to approximately 25% on test data.
  arXiv  Detail & Related papers  (2025-12-20T23:08:18Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• Transformers Are Universally Consistent [14.904264782690639]
  We show that Transformers equipped with softmax-based nonlinear attention are uniformly consistent when tasked with executing Least Squares regression.<n>We derive upper bounds on the empirical error which, in the regime, decay at a provable rate of $mathcalO(t-1/2d)$, where $t$ denotes the number of input tokens and $d$ the embedding dimensionality.
  arXiv  Detail & Related papers  (2025-05-30T12:39:26Z)
• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• Posterior Collapse and Latent Variable Non-identifiability [54.842098835445]
  We propose a class of latent-identifiable variational autoencoders, deep generative models which enforce identifiability without sacrificing flexibility. Across synthetic and real datasets, latent-identifiable variational autoencoders outperform existing methods in mitigating posterior collapse and providing meaningful representations of the data.
  arXiv  Detail & Related papers  (2023-01-02T06:16:56Z)
• Intrinsic dimension estimation for discrete metrics [65.5438227932088]
  In this letter we introduce an algorithm to infer the intrinsic dimension (ID) of datasets embedded in discrete spaces. We demonstrate its accuracy on benchmark datasets, and we apply it to analyze a metagenomic dataset for species fingerprinting. This suggests that evolutive pressure acts on a low-dimensional manifold despite the high-dimensionality of sequences' space.
  arXiv  Detail & Related papers  (2022-07-20T06:38:36Z)
• SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
  Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-11-25T03:53:43Z)
• A Non-Linear Structural Probe [43.50268085775569]
  We study the case of a structural probe, which aims to investigate the encoding of syntactic structure in contextual representations. By observing that the structural probe learns a metric, we are able to kernelize it and develop a novel non-linear variant. We test on 6 languages and find that the radial-basis function (RBF) kernel, in conjunction with regularization, achieves a statistically significant improvement.
  arXiv  Detail & Related papers  (2021-05-21T07:53:10Z)
• The Low-Dimensional Linear Geometry of Contextualized Word Representations [27.50785941238007]
  We study the linear geometry of contextualized word representations in ELMO and BERT. We show that a variety of linguistic features are encoded in low-dimensional subspaces.
  arXiv  Detail & Related papers  (2021-05-15T00:58:08Z)
• Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models [22.43510769150502]
  It is not entirely clear what aspects of sentence-level syntax are captured by vector-based language representations. We show that Transformers build sensitivity to larger parts of the sentence along their layers, and that hierarchical phrase structure plays a role in this process.
  arXiv  Detail & Related papers  (2021-04-15T16:30:31Z)
• A Comparative Study on Structural and Semantic Properties of Sentence Embeddings [77.34726150561087]
  We propose a set of experiments using a widely-used large-scale data set for relation extraction. We show that different embedding spaces have different degrees of strength for the structural and semantic properties. These results provide useful information for developing embedding-based relation extraction methods.
  arXiv  Detail & Related papers  (2020-09-23T15:45:32Z)

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.