Nura Aljaafari
4 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(2)
Machine Learning
(2)
Natural Language Processing
(2)
Core Methods
(2)
Architectures
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Understanding
(1)
Keywords
representation learning
(2)
mechanistic interpretability
(2)
semantic consistency
(1)
linguistic knowledge
(1)
mutual information
(1)
layer-wise analysis
(1)
language model
(1)
linguistic feature
(1)
synthetic corpus
(1)
causal tracing
(1)
activation patching
(1)
reverse dictionary
(1)
large language model
(1)
transformer model
(1)
compositional generalisation
(1)
mutual information regularisation
(1)
feature fragmentation
(1)
layer-wise stability
(1)
syntactic emergence
(1)
compositional robustness
(1)
Papers
Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models
CoNLL 2026
Where Do LLMs Compose Meaning? A Layerwise Analysis of Compositional Robustness
EACL 2026
CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
EMNLP 2025
TRACE: Training and Inference-Time Interpretability Analysis for Language Models
EMNLP 2025