让手机端大模型更准更快地提取结构化信息
Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models
- 分两阶段：先选合适信息模板，再基于模板提取
- 在多个数据集上准确率提升，推理速度显著加快
- 适合移动端部署，尤其适合多类型信息提取场景
信息抽取（IE）在自然语言处理中至关重要，可将非结构化文本转化为结构化知识。在资源受限设备上部署计算密集型大语言模型（LLMs）进行信息抽取面临诸多挑战，如幻觉、上下文长度有限和高延迟，尤其是在处理多种抽取模式时。为此，我们提出一种适配设备端LLM的两阶段信息抽取方法——双LoRA增量模式缓存（DLISC），在有效性与效率上均有所提升。DLISC采用识别LoRA模块检索与查询最相关的模式，再通过抽取LoRA模块基于选定模式执行信息抽取。为加速推理，引入增量模式缓存机制，减少重复计算，显著提升效率。在多个信息抽取数据集上的实验表明，该方法在有效性和效率方面均有明显改进。
原文摘要 · Abstract (English)
Information extraction (IE) plays a crucial role in natural language processing (NLP) by converting unstructured text into structured knowledge. Deploying computationally intensive large language models (LLMs) on resource-constrained devices for information extraction is challenging, particularly due to issues like hallucinations, limited context length, and high latency-especially when handling diverse extraction schemas. To address these challenges, we propose a two-stage information extraction approach adapted for on-device LLMs, called Dual-LoRA with Incremental Schema Caching (DLISC), which enhances both schema identification and schema-aware extraction in terms of effectiveness and efficiency. In particular, DLISC adopts an Identification LoRA module for retrieving the most relevant schemas to a given query, and an Extraction LoRA module for performing information extraction based on the previously selected schemas. To accelerate extraction inference, Incremental Schema Caching is incorporated to reduce redundant computation, substantially improving efficiency. Extensive experiments across multiple information extraction datasets demonstrate notable improvements in both effectiveness and efficiency.
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。