Picture for Amr Keleg

Amr Keleg

LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?

Add code
Mar 19, 2025
Viaarxiv icon

NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task

Add code
Jul 06, 2024
Viaarxiv icon

Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets

Add code
May 18, 2024
Figure 1 for Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets
Figure 2 for Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets
Figure 3 for Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets
Viaarxiv icon

ALDi: Quantifying the Arabic Level of Dialectness of Text

Add code
Oct 20, 2023
Viaarxiv icon

Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification

Add code
Oct 20, 2023
Figure 1 for Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification
Figure 2 for Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification
Figure 3 for Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification
Figure 4 for Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification
Viaarxiv icon

DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models

Add code
Jun 08, 2023
Figure 1 for DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models
Figure 2 for DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models
Figure 3 for DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models
Figure 4 for DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models
Viaarxiv icon