Cover Image

Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Diera, Andor, Scherp, Ansgar
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

Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search
by: Diera, Andor, et al.
Published: (2024)

Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck
by: Diera, Andor, et al.
Published: (2024)

Memorization of Named Entities in Fine-tuned BERT Models
by: Diera, Andor, et al.
Published: (2022)

Are We Really Making Much Progress in Text Classification? A Comparative Review
by: Galke, Lukas, et al.
Published: (2022)

Multi-View Structural Graph Summaries
by: Frank, Jonatan, et al.
Published: (2024)

Semantic Source Code Segmentation using Small and Large Language Models
by: Dahou, Abdelhalim, et al.
Published: (2025)

CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents
by: Karl, Fabian, et al.
Published: (2025)

Text Role Classification in Scientific Charts Using Multimodal Transformers
by: Kim, Hye Jin, et al.
Published: (2024)

On the Anatomy of Real-World R Code for Static Analysis
by: Sihler, Florian, et al.
Published: (2024)

Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
by: Deng, Ruixuan, et al.
Published: (2025)

Do Language Models Encode Knowledge of Linguistic Constraint Violations?
by: Hardy, et al.
Published: (2026)

Do LLMs Encode Frame Semantics? Evidence from Frame Identification
by: Chundru, Jayanth Krishna, et al.
Published: (2025)

GLaMoR: Consistency Checking of OWL Ontologies using Graph Language Models
by: Mücke, Justin, et al.
Published: (2025)

How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders
by: McCoubrey, Michael, et al.
Published: (2026)

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe
by: Shen, Gaofei, et al.
Published: (2026)

Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction
by: Mtumbuka, Frank, et al.
Published: (2023)

Your Extreme Multi-label Classifier is Secretly a Hierarchical Text Classifier for Free
by: Bertalis, Nerijus, et al.
Published: (2024)

How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
by: Ju, Tianjie, et al.
Published: (2024)

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders
by: Deng, Boyi, et al.
Published: (2025)

Large Language Models Encode Semantics and Alignment in Linearly Separable Representations
by: Saglam, Baturay, et al.
Published: (2025)

What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?
by: Ryu, Koki, et al.
Published: (2026)

Do BERT Embeddings Encode Narrative Dimensions? A Token-Level Probing Analysis of Time, Space, Causality, and Character in Fiction
by: Bei, Beicheng, et al.
Published: (2026)

Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
by: Eisenstein, Jacob, et al.
Published: (2022)

Enhancing Building Semantics Preservation in AI Model Training with Large Language Model Encodings
by: Jang, Suhyung, et al.
Published: (2026)

Probing Large Language Models for Scalar Adjective Lexical Semantics and Scalar Diversity Pragmatics
by: Lin, Fangru, et al.
Published: (2024)

Semantic Structure of Feature Space in Large Language Models
by: Kozlowski, Austin C., et al.
Published: (2026)

Probing Multimodal Large Language Models for Global and Local Semantic Representations
by: Tao, Mingxu, et al.
Published: (2024)

Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Mindset in Large Language Models
by: Corso, Francesco, et al.
Published: (2025)

Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!
by: Wildenburg, Frank, et al.
Published: (2024)

Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries
by: Gondil, Tanay
Published: (2026)

Do Large Language Models Grasp The Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgish
by: Li, Lujun, et al.
Published: (2025)

Emergence of Linear Truth Encodings in Language Models
by: Ravfogel, Shauli, et al.
Published: (2025)

Language Models Encode the Value of Numbers Linearly
by: Zhu, Fangwei, et al.
Published: (2024)

Time is Encoded in the Weights of Finetuned Language Models
by: Nylund, Kai, et al.
Published: (2023)

A Comprehensive Evaluation of Semantic Relation Knowledge of Pretrained Language Models and Humans
by: Cao, Zhihan, et al.
Published: (2024)

SparseD: Sparse Attention for Diffusion Language Models
by: Wang, Zeqing, et al.
Published: (2025)

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
by: Deng, Boyi, et al.
Published: (2026)

Self-Aware Knowledge Probing: Evaluating Language Models' Relational Knowledge through Confidence Calibration
by: Kissling, Christopher, et al.
Published: (2026)

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
by: Shi, Wei, et al.
Published: (2025)

How to Encode Domain Information in Relation Classification
by: Bassignana, Elisa, et al.
Published: (2024)