CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
This addresses a key limitation in LLMs for AI applications requiring systematic reasoning, though it is incremental as it reinforces existing structures rather than introducing new capabilities.
The paper tackles the problem of compositional generalization in large language models (LLMs) by proposing CARMA, an intervention that uses mutual information regularization and layer-wise constraints to enhance stability and robustness, resulting in reduced variability from fine-tuning and improved compositional reasoning.
Large language models (LLMs) struggle with compositional generalisation, limiting their ability to systematically combine learned components to interpret novel inputs. While architectural modifications, fine-tuning, and data augmentation improve compositionality, they often have limited adaptability, face scalability constraints, or yield diminishing returns on real data. To address this, we propose CARMA, an intervention that enhances the stability and robustness of compositional reasoning in LLMs while preserving fine-tuned performance. CARMA employs mutual information regularisation and layer-wise stability constraints to mitigate feature fragmentation, ensuring structured representations persist across and within layers. We evaluate CARMA on inverse dictionary modelling and sentiment classification, measuring its impact on semantic consistency, performance stability, and robustness to lexical perturbations. Results show that CARMA reduces the variability introduced by fine-tuning, stabilises token representations, and improves compositional reasoning. While its effectiveness varies across architectures, CARMA's key strength lies in reinforcing learned structures rather than introducing new capabilities, making it a scalable auxiliary method. These findings suggest that integrating CARMA with fine-tuning can improve compositional generalisation while maintaining task-specific performance in LLMs.