Image de couverture de livre

Finding Meaning in Embeddings: Concept Separation Curves

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Keuren, Paul, Ponsen, Marc, Bagheri, Robert Ayoub
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exploring Cultural Variations in Moral Judgments with Large Language Models
par: Mohammadi, Hadi, et autres
Publié: (2025)

Correspondence Analysis and PMI-Based Word Embeddings: A Comparative Study
par: Qi, Qianqian, et autres
Publié: (2024)

Large Language Models as Mirrors of Societal Moral Standards
par: Papadopoulou, Evi, et autres
Publié: (2024)

LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics
par: Meijer, Mijntje, et autres
Publié: (2024)

Improving Stance Detection by Leveraging Measurement Knowledge from Social Sciences: A Case Study of Dutch Political Tweets and Traditional Gender Role Division
par: Fang, Qixiang, et autres
Publié: (2022)

Do Large Language Models Understand Morality Across Cultures?
par: Mohammadi, Hadi, et autres
Publié: (2025)

Explainability in Practice: A Survey of Explainable NLP Across Various Domains
par: Mohammadi, Hadi, et autres
Publié: (2025)

Explainability-Based Token Replacement on LLM-Generated Text
par: Mohammadi, Hadi, et autres
Publié: (2025)

Estimating Text Similarity based on Semantic Concept Embeddings
par: der Brück, Tim vor, et autres
Publié: (2024)

Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection
par: Hammal, Ayoub, et autres
Publié: (2024)

Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
par: Mohammadi, Hadi, et autres
Publié: (2025)

Mind the Style: Impact of Communication Style on Human-Chatbot Interaction
par: Derner, Erik, et autres
Publié: (2026)

Norm of Mean Contextualized Embeddings Determines their Variance
par: Yamagiwa, Hiroaki, et autres
Publié: (2024)

Named Entity Recognition in Context
par: Brisson, Colin, et autres
Publié: (2025)

Lifelong Event Detection with Embedding Space Separation and Compaction
par: Qin, Chengwei, et autres
Publié: (2024)

Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservation
par: Cripwell, Liam, et autres
Publié: (2024)

Partial Colexifications Improve Concept Embeddings
par: Rubehn, Arne, et autres
Publié: (2025)

Toward Culturally Grounded Natural Language Processing
par: Nezhad, Sina Bagheri
Publié: (2026)

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
par: Dumas, Clément, et autres
Publié: (2024)

Ontology Completion with Natural Language Inference and Concept Embeddings: An Analysis
par: Li, Na, et autres
Publié: (2024)

Domain Embeddings for Generating Complex Descriptions of Concepts in Italian Language
par: Maisto, Alessandro
Publié: (2024)

The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure
par: Fan, Yu, et autres
Publié: (2025)

Transfer Learning with Clinical Concept Embeddings from Large Language Models
par: Gao, Yuhe, et autres
Publié: (2024)

Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions
par: Sastre, Ignacio, et autres
Publié: (2026)

Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings
par: Kteich, Hanane, et autres
Publié: (2024)

Linearly-Interpretable Concept Embedding Models for Text Analysis
par: De Santis, Francesco, et autres
Publié: (2024)

Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings
par: Hara, Tomomasa, et autres
Publié: (2026)

Geometric Patterns of Meaning: A PHATE Manifold Analysis of Multi-lingual Embeddings
par: Gong, Wen G
Publié: (2025)

EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
par: Mohammadi, Hadi, et autres
Publié: (2025)

Ad-hoc Concept Forming in the Game Codenames as a Means for Evaluating Large Language Models
par: Hakimov, Sherzod, et autres
Publié: (2025)

Geometric Structures and Patterns of Meaning: A PHATE Manifold Analysis of Chinese Character Embeddings
par: Gong, Wen G.
Publié: (2025)

CALE : Concept-Aligned Embeddings for Both Within-Lemma and Inter-Lemma Sense Differentiation
par: Liétard, Bastien, et autres
Publié: (2025)

Latent Structure Modulation in Large Language Models Through Stochastic Concept Embedding Transitions
par: Whitaker, Stefan, et autres
Publié: (2025)

Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks
par: Nezhad, Sina Bagheri, et autres
Publié: (2025)

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models
par: Chen, Kexin, et autres
Publié: (2025)

CoLLEGe: Concept Embedding Generation for Large Language Models
par: Teehan, Ryan, et autres
Publié: (2024)

SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation
par: Nezhad, Sina Bagheri, et autres
Publié: (2025)

Enhancing Safety of Large Language Models via Embedding Space Separation
par: Zhao, Xu, et autres
Publié: (2026)

When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training
par: Körner, Felicia, et autres
Publié: (2026)

On the Rejection Criterion for Proxy-based Test-time Alignment
par: Hammal, Ayoub, et autres
Publié: (2026)