用小模型+LoRA微调，在普通电脑上实现多任务放射科AI。
RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
- 用LoRA微调30亿~40亿参数小模型，适配多种放射科任务。
- 微调后准确率提升超50%，关键任务如分期准确率提高89%。
- 模型可量化至1.8-2.4GB，CPU上每秒生成4-8个词，适合临床部署。
大语言模型在放射科有潜力，但计算需求高，难以在资源受限的临床环境中部署。我们研究了30亿至40亿参数的小语言模型（SLMs）通过LoRA微调是否能在放射科实现强多任务表现，从而实现在消费级CPU上的部署。我们在16.2万份样本上训练Qwen2.5-3B-Instruct和Qwen3-4B，覆盖9项放射科任务：10个系统的RADS分类、报告生成、时间对比、放射科NLI、NER、异常检测、分期（N/M）、以及放射科问答，数据来自12个公开数据集。两个模型在每项任务上均使用最多500个保留测试样本进行评估，采用标准化指标。主要发现包括：(1) LoRA微调显著优于零样本基线（RADS准确率提升53%，NLI提升60%，分期提升89%）；(2) 两模型表现出互补优势——Qwen2.5在结构化生成任务中更优，而Qwen3在抽取类任务中占优；(3) 一个任务外的组合集成模型在所有任务上达到最佳性能；(4) 使用微调模型进行少样本提示反而降低性能，表明在专业领域，LoRA适应比上下文学习更有效；(5) 模型可量化为GGUF格式（约1.8-2.4GB），在消费级硬件上以4-8个词/秒的速度运行。本工作证明，经高效微调的小模型（我们统称为RadLite）可作为无需GPU支持、完全部署于消费级硬件的实用多任务放射科AI助手。代码与模型见https://github.com/RadioX-Labs/RadLite。
原文摘要 · Abstract (English)
Large language models (LLMs) show promise in radiology but their deployment is limited by computational requirements that preclude use in resource-constrained clinical environments. We investigate whether small language models (SLMs) of 3-4 billion parameters can achieve strong multi-task radiology performance through LoRA fine-tuning, enabling deployment on consumer-grade CPUs. We train Qwen2.5-3B-Instruct and Qwen3-4B on 162K samples spanning 9 radiology tasks - RADS classification across 10 systems, impression generation, temporal comparison, radiology NLI, NER, abnormality detection, N/M staging, and radiology Q&A - compiled from 12 public datasets. Both models are evaluated on up to 500 held-out test samples per task with standardized metrics. Our key findings are: (1) LoRA fine-tuning dramatically improves performance over zero-shot baselines (RADS accuracy +53%, NLI +60%, N-staging +89%); (2) the two models exhibit complementary strengths - Qwen2.5 excels at structured generation tasks while Qwen3 dominates extractive tasks; (3) a task-outed oracle ensemble combining both models achieves the best performance across all tasks; (4) few-shot prompting with fine-tuned models hurts performance, demonstrating that LoRA adaptation is more effective than in-context learning for specialized domains; and (5) models can be quantized to GGUF format (~1.8-2.4GB) for CPU deployment at 4-8 tokens/second on consumer hardware. Our work demonstrates that small, efficiently fine-tuned models - which we collectively call RadLite - can serve as practical multi-task radiology AI assistants deployable entirely on consumer hardware without GPU requirements. Code and models are available at https://github.com/RadioX-Labs/RadLite
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。