Quoc-Dai Luong Tran

Enhancing Small Language Models via Evolutionary Data Generation and Context-Aware DPO for Low-Resource Legal Question Answering

Results demonstrate that integrating a rule-based virtual legal assistant with contrastive retrieval and preference optimization provides an effective and computationally efficient strategy for aligning the legal reasoning capabilities of small language models, offering a scalable solution for legal question answering in specialized low-resource environments.