Cover Image

Polar probe linearly decodes semantic structures from LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Diego-Simón, Pablo J., Orhan, Pierre, Chemla, Emmanuel, Lakretz, Yair, King, Jean-Rémi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Probing Syntax in Large Language Models: Successes and Remaining Challenges
by: Diego-Simón, Pablo J., et al.
Published: (2025)

Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks
by: Orhan, Pierre, et al.
Published: (2026)

A polar coordinate system represents syntax in large language models
by: Diego-Simón, Pablo, et al.
Published: (2024)

Metric Learning Encoding Models: A Multivariate Framework for Interpreting Neural Representations
by: Jalouzot, Louis, et al.
Published: (2024)

A Neural Model for Word Repetition
by: Dager, Daniel, et al.
Published: (2025)

What Makes Two Language Models Think Alike?
by: Salle, Jeanne, et al.
Published: (2024)

Meta-Learning Neural Mechanisms rather than Bayesian Priors
by: Goodale, Michael, et al.
Published: (2025)

MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings
by: Rambaud, Victor, et al.
Published: (2025)

Disentanglement and Compositionality of Letter Identity and Letter Position in Variational Auto-Encoder Vision Models
by: Bianchi, Bruno, et al.
Published: (2024)

Biasless Language Models Learn Unnaturally: How LLMs Fail to Distinguish the Possible from the Impossible
by: Ziv, Imry, et al.
Published: (2025)

No Such Thing as a General Learner: Language models and their dual optimization
by: Chemla, Emmanuel, et al.
Published: (2024)

Bridging the Empirical-Theoretical Gap in Neural Network Formal Language Learning Using Minimum Description Length
by: Lan, Nur, et al.
Published: (2024)

Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach
by: Poli, Maxime, et al.
Published: (2024)

fastabx: A library for efficient computation of ABX discriminability
by: Poli, Maxime, et al.
Published: (2025)

Optimizing fMRI Data Acquisition for Decoding Natural Speech with Limited Participants
by: Jalouzot, Louis, et al.
Published: (2025)

The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation
by: Guerin, Nicolas, et al.
Published: (2024)

Large Language Models as Proxies for Theories of Human Linguistic Cognition
by: Ziv, Imry, et al.
Published: (2025)

A Minimum Description Length Approach to Regularization in Neural Networks
by: Abudy, Matan, et al.
Published: (2025)

From Minutes to Days: Scaling Intracranial Speech Decoding with Supervised Pretraining
by: Evanson, Linnea, et al.
Published: (2025)

DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units
by: Poli, Maxime, et al.
Published: (2026)

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
by: Zhao, Xuandong, et al.
Published: (2024)

The quasi-semantic competence of LLMs: a case study on the part-whole relation
by: Proietti, Mattia, et al.
Published: (2025)

CyberPal.AI: Empowering LLMs with Expert-Driven Cybersecurity Instructions
by: Levi, Matan, et al.
Published: (2024)

Benchmarking LLMs and SLMs for patient reported outcomes
by: Marengo, Matteo, et al.
Published: (2024)

PARHAF, a human-authored corpus of clinical reports for fictitious patients in French
by: Tannier, Xavier, et al.
Published: (2026)

Evidence for systematic semantic structure in individual phonemes
by: Zhao, Gexin
Published: (2026)

Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel
by: King, Brendan, et al.
Published: (2024)

On convexity and efficiency in semantic systems
by: Imel, Nathaniel, et al.
Published: (2026)

Universal computation is intrinsic to language model decoding
by: Lewandowski, Alex, et al.
Published: (2026)

Automata-based constraints for language model decoding
by: Koo, Terry, et al.
Published: (2024)

Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding
by: Olak, Michal, et al.
Published: (2026)

IYKYK: Using language models to decode extremist cryptolects
by: de Kock, Christine, et al.
Published: (2025)

A* shortest string decoding for non-idempotent semirings
by: Gorman, Kyle, et al.
Published: (2022)

An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analyses
by: Chandra, Rohitash, et al.
Published: (2025)

Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yorùbá
by: Osakuade, Opeyemi, et al.
Published: (2026)

Dynamic semantic networks for exploration of creative thinking
by: Georgiev, Danko D., et al.
Published: (2025)

Definition generation for lexical semantic change detection
by: Fedorova, Mariia, et al.
Published: (2024)

Principles of semantic and functional efficiency in grammatical patterning
by: Cheng, Emily, et al.
Published: (2024)

Semantic Tree-Width and Path-Width of Conjunctive Regular Path Queries
by: Figueira, Diego, et al.
Published: (2022)

The role of System 1 and System 2 semantic memory structure in human and LLM biases
by: Abramski, Katherine, et al.
Published: (2026)