← Back to all news
Hugging Face Trending Papers

Language Models Represent and Transform Concepts with Shared Geometry

How concepts are represented in neural networks is a fundamental question in machine learning. The dominant view treats concept representations as stationary geometric objects.

Related stories

arXiv Machine Learning
Jul 1

Symmetry in language statistics shapes the geometry of model representations

arXiv:2602. 15029v3 Announce Type: replace Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' latitudes and longitudes can be decoded using a linear probe.

By Dhruva Karkada, Daniel J. Korchinski, Andres Nava, Matthieu Wyart, Yasaman Bahri
llmsragnlp
More like this →
arXiv Computation and Language
Aug 27

The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers

The paper studies how transformer representations evolve across layers by examining the intrinsic dimensionality (ID) of token embeddings and their neighborhood structures. It finds that closed‑class tokens expand and collapse earlier than open‑class tokens, and that these changes are linked to shifts in local geometry. The authors compare encoder and decoder models, showing distinct layer‑wise behaviors, and demonstrate that geometric features alone can predict a token’s part‑of‑speech and reveal how semantic content changes across layers.

By Samuele Vallisa, Federico Ravenda, Claudio Palominos, Rui He, Andrea Raballo, Antonietta Mira, Philipp Homan, Wolfram Hinzen
llmsnlp
More like this →
arXiv Machine Learning
Sep 11

The information geometry of large language models is shared, learned, and controllable

The paper investigates how large language models (LLMs) share a common Fisher‑Rao geometry in their next‑token probability distributions, revealing that behaviour largely determines this geometry while activation geometry depends on coordinate choices. Across transformer, state‑space, and recurrent architectures, output geometries align more closely than activation geometries, and this shared structure facilitates semantic‑category transfer and improves agreement with human word choices as models scale and train. The study further demonstrates that geometry can guide minimum‑disturbance interventions, enabling reusable control that preserves behaviour better than Euclidean methods and enhances steering, editing, attribution, dictionary learning, and fine‑tuning.

By Dario Picozzi
llmsfine-tuning
More like this →
arXiv Machine Learning
1d ago

Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models

The paper extends mechanistic interpretability of large language models by modeling concepts as low‑dimensional non‑linear manifolds rather than linear subspaces. It introduces a concept‑based alignment (CBA) score to compare these manifolds across layers and models, revealing block structures in intermediate layers, a shift from syntax‑dominated to mixed syntactic‑semantic concepts, and training‑dependent multilingual sharing. The study also shows that alignment patterns differ across model families and training stages, with adjacent stages aligning more closely than distant ones.

By Tido Specht, Elias Benedict Krey, Nils Neukirch, Nils Strodthoff
llmscomputer-visionreinforcement-learningfine-tuningsafety
More like this →
arXiv Machine Learning
Jul 15

Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale

arXiv:2603. 06592v2 Announce Type: replace-cross Abstract: Contemporary studies in mechanistic interpretability have uncovered many puzzling phenomena in the neural information processing of Transformer-based language models, such as induction heads, function vectors, and the Hydra effect.

By Jonas Rohweder, Subhabrata Dutta, Iryna Gurevych
llmssafety
More like this →