arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09434cs.CLcs.AI
收藏

HySem:一种面向非结构化表格提取的上下文长度优化LLM流水线

HySem: A context length optimized LLM pipeline for unstructured tabular extraction

Indian Institute of Science(印度科学学院);JNResearch Labs LLP(JNResearch实验室有限责任公司)

Narayanan PP, Anantharaman Palacode Narayana Iyer

AI总结:

针对制药行业非结构化表格提取中LLM存在的准确性与上下文长度限制问题,提出采用上下文长度优化技术的HySem流水线,适配中小药企成本隐私需求,在开源模型中准确率领先,性能对标GPT-4o,可支持更大表格处理。

摘要:

制药行业的监管合规报告依赖详细的表格,但由于格式非结构化且内容随意,这些表格除合规用途外往往未得到充分利用。由于表格呈现形式多样,提取表格数据并对其进行语义表示颇具挑战。大语言模型(LLM)在语义表示方面展现出巨大潜力,但面临准确性和上下文大小限制的难题,这两点是行业应用的关键考量因素。我们提出HySem,这一流水线采用一种新颖的上下文长度优化技术,可从HTML表格生成准确的语义JSON表示。该方法使用定制微调模型,专为对成本和隐私敏感的中小型制药企业设计。HySem基于商用硬件运行并采用开源模型,在准确性上优于同类开源模型,与OpenAI GPT-4o基准测试相比性能具备竞争力,且有效解决了上下文长度限制问题——这是支持更大表格的关键因素。

英文摘要:

Regulatory compliance reporting in the pharmaceutical industry relies on detailed tables, but these are often under-utilized beyond compliance due to their unstructured format and arbitrary content. Extracting and semantically representing tabular data is challenging due to diverse table presentations. Large Language Models (LLMs) demonstrate substantial potential for semantic representation, yet they encounter challenges related to accuracy and context size limitations, which are crucial considerations for the industry applications. We introduce HySem, a pipeline that employs a novel context length optimization technique to generate accurate semantic JSON representations from HTML tables. This approach utilizes a custom fine-tuned model specifically designed for cost- and privacy-sensitive small and medium pharmaceutical enterprises. Running on commodity hardware and leveraging open-source models, HySem surpasses its peer open-source models in accuracy and provides competitive performance when benchmarked against OpenAI GPT-4o and effectively addresses context length limitations, which is a crucial factor for supporting larger tables.

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。

↑