Efficient Multi-Task Inferencing with a Shared Backbone and Lightweight Task-Specific Adapters for Automatic Scoring
This incremental improvement addresses efficiency and cost for deploying AI in educational assessment, benefiting educators and institutions.
The paper tackled the problem of scaling AI for automated scoring in education by proposing a shared backbone with lightweight adapters, achieving competitive performance (average QWK 0.848 vs. 0.888 for full fine-tuning) while reducing GPU memory by 60% and inference latency by 40%.
The integration of Artificial Intelligence (AI) in education requires scalable and efficient frameworks that balance performance, adaptability, and cost. This paper addresses these needs by proposing a shared backbone model architecture enhanced with lightweight LoRA adapters for task-specific fine-tuning, targeting the automated scoring of student responses across 27 mutually exclusive tasks. By achieving competitive performance (average QWK of 0.848 compared to 0.888 for fully fine-tuned models) while reducing GPU memory consumption by 60% and inference latency by 40%, the framework demonstrates significant efficiency gains. This approach aligns with the workshop's focus on improving language models for educational tasks, creating responsible innovations for cost-sensitive deployment, and supporting educators by streamlining assessment workflows. The findings underscore the potential of scalable AI to enhance learning outcomes while maintaining fairness and transparency in automated scoring systems.