利用大语言模型增强学术论文摘要和全文内容中的知识实体关系抽取

arXiv cs.CL 论文
entity-relation-extraction large-language-models knowledge-extraction nlp lora academic-papers

摘要

该论文评估了多种基于大语言模型的策略，用于从学术摘要和全文中提取知识实体关系，发现经 LoRA 适配的 T5 模型取得了最高的宏平均 F1 分数，而混合使用小语言模型与大语言模型的策略进一步提升了性能。

arXiv:2610.41552v1 Announce Type: new Abstract: This study investigates the effectiveness of large pre-trained language models (LLMs) for knowledge entity relation extraction (KERE) from academic papers. Existing studies have examined individual types of LLM-based strategies and evaluated model performance using metrics such as precision and recall. To provide a broader evaluation, this study investigates multiple strategies, including closed-source LLM-based CoT prompting, LoRA-adapted open-source LLMs, LLM-enhanced small pre-trained language models (SLMs), and SLM-enhanced closed-source LLMs. In addition, this study introduces two strategies, namely SLM-enhanced open-source LLMs and closed-source LLM-enhanced open-source LLMs. These strategies are evaluated from multiple perspectives, including metrics, their ability to mitigate errors observed in SLMs, and potential directions for model optimization. This study manually constructs two annotated datasets in the NLP domain, covering Abstract and Full-Text datasets. Experimental results show that the LoRA-adapted T5 model achieves the highest macro F1 scores of 0.7408 and 0.7013 on the Abstract and Full-Text datasets, respectively. SLMs also benefit from LLM-generated entity descriptions under the LLM-enhanced SLM strategy. Error analysis further reveals that the effectiveness of LLM-based strategies in mitigating SLM errors varies across error types. Based on the identified limitations and error patterns of these strategies, several optimization directions are proposed. In addition, combining strategies with different error patterns further improves KERE performance.
查看原文
查看缓存全文

缓存时间: 2026/11/02 09:30 

# Enhancing Knowledge Entity Relation Extraction in Abstracts and Full-text Content of Academic Articles Using Large Language Models
Source: [https://arxiv.org/abs/2610.41552](https://arxiv.org/abs/2610.41552)
[View PDF](https://arxiv.org/pdf/2610.41552)

> Abstract:This study investigates the effectiveness of large pre\-trained language models \(LLMs\) for knowledge entity relation extraction \(KERE\) from academic papers\. Existing studies have examined individual types of LLM\-based strategies and evaluated model performance using metrics such as precision and recall\. To provide a broader evaluation, this study investigates multiple strategies, including closed\-source LLM\-based CoT prompting, LoRA\-adapted open\-source LLMs, LLM\-enhanced small pre\-trained language models \(SLMs\), and SLM\-enhanced closed\-source LLMs\. In addition, this study introduces two strategies, namely SLM\-enhanced open\-source LLMs and closed\-source LLM\-enhanced open\-source LLMs\. These strategies are evaluated from multiple perspectives, including metrics, their ability to mitigate errors observed in SLMs, and potential directions for model optimization\. This study manually constructs two annotated datasets in the NLP domain, covering Abstract and Full\-Text datasets\. Experimental results show that the LoRA\-adapted T5 model achieves the highest macro F1 scores of 0\.7408 and 0\.7013 on the Abstract and Full\-Text datasets, respectively\. SLMs also benefit from LLM\-generated entity descriptions under the LLM\-enhanced SLM strategy\. Error analysis further reveals that the effectiveness of LLM\-based strategies in mitigating SLM errors varies across error types\. Based on the identified limitations and error patterns of these strategies, several optimization directions are proposed\. In addition, combining strategies with different error patterns further improves KERE performance\.

## Submission history

From: Chengzhi Zhang \[[view email](https://arxiv.org/show-email/4ec71361/2610.41552)\] **\[v1\]**Fri, 30 Oct 2026 10:50:28 UTC \(9,050 KB\)

相似文章

LLM Wiki v2（16分钟阅读）

TLDR AI

本文介绍了一种利用LLM构建个人知识库的模式，为在大语言模型辅助下进行知识管理提供了结构化方法。

使用大型语言模型标注实体匹配的训练数据

arXiv cs.CL

本文研究使用大型语言模型作为教师模型来标注实体匹配的训练数据，结果表明，在机器标注数据上训练的学生模型与在人工标注基准上训练的模型性能相当，并且具有显著的成本和速度优势。

追踪大语言模型中的关系知识回忆

arXiv cs.CL

研究者通过探测每个注意力头的贡献，追踪大语言模型如何回忆关系事实，发现这些贡献是强线性特征，其保真度与关系特异性及实体连接度相关。