Abstract
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.
Abstract (translated)
大型语言模型(LLMs)在组合泛化方面存在困难,限制了它们系统地结合已学组件来解释新输入的能力。尽管架构修改、微调和数据增强可以改善组合性,但这些方法通常适应性有限、面临规模扩展的约束或在实际数据上收益递减。为解决这一问题,我们提出了CARMA干预措施,旨在提高大型语言模型中组合推理的稳定性和鲁棒性,同时保持微调后的性能。 CARMA采用互信息正则化和逐层稳定性约束来缓解特征碎片化现象,确保跨层和内部层次结构化的表示持续存在。我们在逆词典建模和情感分类任务上评估了CARMA的效果,并对其对语义一致性、性能稳定性和词汇扰动鲁棒性的效果进行了测量。结果显示,CARMA减少了微调引入的变异性,稳定了令牌表示,并提高了组合推理能力。尽管其有效性在不同的架构中有所不同,但CARMA的关键优势在于强化已学结构而不是引入新的功能,使其成为一种可扩展的支持性方法。 这些发现表明,在大型语言模型中结合使用CARMA和微调可以改进组合泛化同时保持特定任务的性能。
URL
https://arxiv.org/abs/2502.11066