Verbalizable Representations Form a Global Workspace in Language Models

• URL: http://arxiv.org/abs/2607.15495v1
• Date: Thu, 16 Jul 2026 22:54:30 GMT
• Title: Verbalizable Representations Form a Global Workspace in Language Models
• Abstract summary: We present evidence that an analogous functional distinction has emerged in large language models.<n>We identify the representations a model is poised to verbalize at any point in its processing.<n>We find that language models maintain a small, privileged set of representations bearing some of the functional hallmarks of conscious access.
• Score: 13.088673968096884
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning. In this paper, we present evidence that an analogous functional distinction has emerged in large language models. Using a new interpretability technique, the Jacobian lens, we identify the representations a model is poised to verbalize at any point in its processing. These representations, which we collectively call the J-space, exhibit the functional properties characteristic of a global workspace: their contents can be reported, deliberately summoned and held, used to carry the intermediate steps of silent reasoning, and passed as arguments to arbitrary downstream computations, while automatic processing such as text parsing and routine inference proceeds without them. The J-space also has structural signatures that global workspace theory associates with conscious access: it carries coherent content only in an intermediate band of layers, holds on the order of tens of concepts at a time, and is broadcast by the model's weights more widely than other representations. These properties make it a practical window into a model's unspoken thinking. In alignment audits, it reveals strategic deliberation, evaluation awareness, and trained-in misaligned dispositions that never appear in the model's outputs. We find that post-training installs the Assistant's point of view in the workspace, and we introduce counterfactual reflection training, which improves behavior by training only what a model would say if interrupted and asked to reflect. These results indicate that language models maintain a small, privileged set of representations bearing some of the functional hallmarks of conscious access, and that decoding these representations sheds light on ongoing cognitive processes.

Related papers

• The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models [2.835219195516112]
  holistic storage is driven by frequency and predictability.<n>All models show evidence of holistic storage driven by frequency and predictability, further supporting usage-based theories of language.
  arXiv  Detail & Related papers  (2026-06-12T00:27:42Z)
• Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding [88.11781604392606]
  This paper defines language representation as the linguistic and symbolic constructs used to map and model the real world.<n>We argue that shaping schemas through advanced language representation is the next frontier for expanding Large Language Models.
  arXiv  Detail & Related papers  (2026-05-10T02:42:29Z)
• Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models [77.98801218316505]
  Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning.<n>We investigate the internal processing of LLMs during in-context concept inference.
  arXiv  Detail & Related papers  (2026-02-08T03:14:39Z)
• A Markov Categorical Framework for Language Modeling [9.910562011343009]
  Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes their representations, and enables complex behaviors, remains elusive.<n>We introduce a new analytical framework that models the single-step generation process as a composition of information-processing stages using the language of Markov categories.<n>This work presents a powerful new lens for understanding how information flows through a model and how the training objective shapes its internal geometry.
  arXiv  Detail & Related papers  (2025-07-25T13:14:03Z)
• Less is More: Local Intrinsic Dimensions of Contextual Language Models [15.934492316122025]
  We introduce a novel perspective based on the geometric properties of contextual latent embeddings to study the effects of training and fine-tuning.<n>We show that the local dimensions provide insights into the model's training dynamics and generalization ability.<n>Our experiments suggest configuring a practical: reductions in the mean local dimension tend to accompany and predict subsequent performance gains.
  arXiv  Detail & Related papers  (2025-06-01T14:30:46Z)
• The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models [40.128112851978116]
  We study how different prompting methods affect the geometry of representations in language models.<n>Our analysis highlights the critical role of input distribution samples and label semantics in few-shot in-context learning.<n>Our work contributes to the theoretical understanding of large language models and lays the groundwork for developing more effective, representation-aware prompting strategies.
  arXiv  Detail & Related papers  (2025-02-11T23:09:50Z)
• A Practical Method for Generating String Counterfactuals [106.98481791980367]
  Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior.<n>We give a method to convert representation counterfactuals into string counterfactuals.<n>The resulting counterfactuals can be used to mitigate bias in classification through data augmentation.
  arXiv  Detail & Related papers  (2024-02-17T18:12:02Z)
• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• Feature Interactions Reveal Linguistic Structure in Language Models [2.0178765779788495]
  We study feature interactions in the context of feature attribution methods for post-hoc interpretability. We work out a grey box methodology, in which we train models to perfection on a formal language classification task. We show that under specific configurations, some methods are indeed able to uncover the grammatical rules acquired by a model.
  arXiv  Detail & Related papers  (2023-06-21T11:24:41Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)

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.