Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: An, Jingmin, Liu, Wei, Wang, Qian, Fang, Fang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.06437
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911366055460864
author An, Jingmin
Liu, Wei
Wang, Qian
Fang, Fang
author_facet An, Jingmin
Liu, Wei
Wang, Qian
Fang, Fang
contents Time functions as a fundamental dimension of human cognition, yet the mechanisms by which Large Language Models (LLMs) encode chronological progression remain opaque. We demonstrate that temporal information in their latent space is organized not as discrete clusters but as a continuous, traversable geometry. We introduce the Time Travel Engine (TTE), an interpretability-driven framework that projects diachronic linguistic patterns onto a shared chronological manifold. Unlike surface-level prompting, TTE directly modulates latent representations to induce coherent stylistic, lexical, and conceptual shifts aligned with target eras. By parameterizing diachronic evolution as a continuous manifold within the residual stream, TTE enables fluid navigation through period-specific "zeitgeists" while restricting access to future knowledge. Furthermore, experiments across diverse architectures reveal topological isomorphism between the temporal subspaces of Chinese and English-indicating that distinct languages share a universal geometric logic of historical evolution. These findings bridge historical linguistics with mechanistic interpretability, offering a novel paradigm for controlling temporal reasoning in neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06437
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models
An, Jingmin
Liu, Wei
Wang, Qian
Fang, Fang
Computation and Language
Time functions as a fundamental dimension of human cognition, yet the mechanisms by which Large Language Models (LLMs) encode chronological progression remain opaque. We demonstrate that temporal information in their latent space is organized not as discrete clusters but as a continuous, traversable geometry. We introduce the Time Travel Engine (TTE), an interpretability-driven framework that projects diachronic linguistic patterns onto a shared chronological manifold. Unlike surface-level prompting, TTE directly modulates latent representations to induce coherent stylistic, lexical, and conceptual shifts aligned with target eras. By parameterizing diachronic evolution as a continuous manifold within the residual stream, TTE enables fluid navigation through period-specific "zeitgeists" while restricting access to future knowledge. Furthermore, experiments across diverse architectures reveal topological isomorphism between the temporal subspaces of Chinese and English-indicating that distinct languages share a universal geometric logic of historical evolution. These findings bridge historical linguistics with mechanistic interpretability, offering a novel paradigm for controlling temporal reasoning in neural networks.
title Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2601.06437