arXiv Computation and Language August 31, 2026 By Marco Baroni, Emily Cheng, Iria de-Dios-Flores, Francesca Franzon

Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations

Read the original on arXiv Computation and Language →

The paper investigates the intrinsic dimension (ID) of large language model (LLM) representations as an indicator of linguistic complexity. By comparing ID across model layers for coordination vs. subordination, right‑branching vs. center‑embedding, and unambiguous vs. ambiguous attachment, the authors find consistent ID differences that align with established complexity contrasts. Experiments across six LLMs, including representational similarity and layer pruning analyses, confirm that more complex phenomena produce higher ID profiles, with peaks occurring at different layers for each contrast.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jul 20

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy

arXiv:2602. 17229v2 Announce Type: replace Abstract: The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics.

By Bianca Raimondi, Maurizio Gabbrielli

llms safety

arXiv Computation and Language

Aug 31

Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy

arXiv:2608.27813v1 Announce Type: new Abstract: Structural probes were introduced by Hewitt and Manning to reconstruct syntactic trees from a neural language model's latent representations. They are...

By Juan Pablo Vigneaux, Mary Kennedy, Khalil Iskarous, Robert Frank, Matilde Marcolli

llms rag

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

llms nlp

arXiv AI

Jul 28

Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures

arXiv:2607. 22699v1 Announce Type: new Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains.

By Supantho Rakshit, Adele Goldberg, Henry Conklin

llms benchmarks

arXiv AI

Sep 2

Uncovering the Computational Ingredients of Human-Like Representations in LLMs

arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...

By Zach Studdiford, Timothy T. Rogers, Kushin Mukherjee, Siddharth Suresh

llms fine-tuning multimodal benchmarks safety

arXiv AI

2d ago

Evaluating Steering Techniques using Human Similarity Judgments

arXiv:2505.19333v2 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) steering techniques focus on task-specific performance, overlooking how well steered representati...

By Zach Studdiford, Timothy T. Rogers, Siddharth Suresh, Kushin Mukherjee

llms safety

One email a morning, machine-written

Related stories

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy

Representation of syntax in LLMs through the lens of linear distance and similarity-aware entropy

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

Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures

Uncovering the Computational Ingredients of Human-Like Representations in LLMs

Evaluating Steering Techniques using Human Similarity Judgments