Papers by Nura Aljaafari
TRACE: Training and Inference-Time Interpretability Analysis for Language Models (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing tools for interpretability analysis of transformer models are post hoc, rely on scalar metrics or require nontrivial integration effort. |
| Approach: | They propose a modular toolkit for training and inference-time interpretability analysis of transformer models. |
| Outcome: | Experiments with autoregressive transformers show that TRACE reveals developmental phenomena overlooked by traditional scalar metrics such as loss or accuracy. |
Where Do LLMs Compose Meaning? A Layerwise Analysis of Compositional Robustness (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing approaches to linguistic compositional processing are limited by hallucinations, limited interpretability and a lack of semantic transparency. |
| Approach: | They propose a method that pooles token representations into linguistic constituents at various layers to improve model reliability and interpretability. |
| Outcome: | Experiments on inverse definition modelling, hypernym and synonym prediction show that semantic composition is not localised to specific layers but distributed across network depth. |
CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) struggle with compositional generalisation, limiting their ability to systematically combine learned components to interpret novel inputs. |
| Approach: | They propose a method that enhances stability and robustness of compositional reasoning in large language models (LLMs) by regularising and preserving layer-wise stability constraints. |
| Outcome: | The proposed method reduces variability, stabilizes token representations, and improves compositional reasoning. |
Emergence and Localisation of Semantic Role Circuits in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Despite displaying semantic competence, large language models’ internal mechanisms that ground abstract semantic structure remain insufficiently characterised. |
| Approach: | They propose a causal-temporal methodology that uses contrastive minimal pairs, edge-attribution circuit discovery, and training-time tracking to characterise semantic-role circuits along three dimensions. |
| Outcome: | The proposed method is applicable to any behaviour isolatable through contrastive minimal pairs, including factual recall, syntactic agreement, and logical reasoning. |