arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.21065cs.CL
收藏

高效多任务推理:共享骨干网络与轻量级任务特定适配器用于自动评分

Efficient Multi-Task Inferencing with a Shared Backbone and Lightweight Task-Specific Adapters for Automatic Scoring

University of Georgia(佐治亚大学)

Ehsan Latif, Xiaoming Zhai

AI总结:

本文提出共享骨干网络与轻量LoRA适配器的架构,在27个自动评分任务上以降低60%内存和40%延迟实现接近全微调的性能(QWK 0.848),兼顾效率与公平。

摘要:

人工智能(AI)在教育中的整合需要可扩展且高效的框架,以平衡性能、适应性和成本。本文通过提出一种共享骨干模型架构,并辅以轻量级LoRA适配器进行任务特定微调,针对27个互斥任务的学生回答自动评分,来满足这些需求。该框架在实现竞争性性能(平均QWK为0.848,而完全微调模型为0.888)的同时,将GPU内存消耗降低了60%,推理延迟降低了40%,展示了显著的效率提升。这种方法与研讨会关注改进教育任务语言模型、为成本敏感部署创造负责任创新以及通过简化评估流程支持教育工作者的目标相一致。研究结果强调了可扩展AI在增强学习成果的同时,保持自动评分系统公平性和透明性的潜力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑