Relation extraction represents a fundamental component in the process of creating knowledge graphs, among other applications. Large language models (LLMs) have been adopted as a promising tool for relation extraction, both in supervised and in-context learning settings. However, in this work we show that their performance still lags behind much smaller architectures when the linguistic graph underlying a text has great complexity. To demonstrate this, we evaluate four LLMs against a graph-based parser on six relation extraction datasets with sentence graphs of varying sizes and complexities. Our results show that the graph-based parser increasingly outperforms the LLMs, as the number of relations in the input documents increases. This makes the much lighter graph-based parser a superior choice in the presence of complex linguistic graphs.
Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs
Institute for Machine Learning and Analytics (IMLA), Offenburg University, Offenburg, Germany（机器学习与分析研究所（IMLA）、奥芬堡大学）；University of Mannheim, Mannheim, Germany（曼海姆大学）
Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language
Faculty of Data and Decision Sciences, Technion - Israel Institute of Technology（以色列理工学院数据与决策科学学院）；Shaare Zedek Medical Center（沙雷泽德克医疗中心）；Faculty of Biomedical Engineering, Technion - Israel Institute of Technology（以色列理工学院生物医学工程学院）；Hospital for Sick Children（病童医院）
提出SMP-BERT提示学习方法，利用报告结构从希伯来语克罗恩病放射学报告中提取结构化信息，显著优于传统微调，尤其在罕见病症检测上（AUC 0.99 vs 0.94，F1 0.84 vs 0.34），推动低资源语言的AI诊断。
Evaluating Temporal Reasoning in Large Language Models: Event Temporal Relation Extraction with Allen's Interval Algebra, Logical Consistency, and Relative Time in Narratives
Islamic University of Technology（伊斯兰科技大学）；Rajshahi University of Engineering & Technology（拉杰沙希工程技术大学）
Zero-Shot End-to-End Relation Extraction in Chinese: A Comparative Study of Gemini, LLaMA and ChatGPT
University of Amsterdam（阿姆斯特丹大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）；Simon Fraser University（西蒙菲莎大学）；Northeastern University（东北大学）
From Judgments to Issues: Structured Extraction of Legal Reasoning with Citation-Hallucination Control
Quantitative and Digital Law Laboratory（量化与数字法律实验室）；CIRSFID - Alma AI, Faculty of Law University of Bologna（CIRSFID - 阿尔玛AI，博洛尼亚大学法学院）；Robert Schuman Centre European University Institute（罗伯特·施曼中心欧洲大学研究所）
LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature
Massachusetts Institute of Technology（麻省理工学院）；Entalpic（Entalpic公司）；URM MAP；LIRIS（LIRIS实验室）；Georgia Tech（佐治亚理工学院）；University of California Santa Barbara（加州大学圣巴巴拉分校）；Chalmers University of Technology（查尔姆斯理工大学）；University of Gothenburg（哥德堡大学）；ETH Zurich（苏黎世联邦理工学院）；EPFL（洛桑联邦理工学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Hugging Face（Hugging Face公司）；Imperial College London（帝国理工学院）
Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO
HKUST Hong Kong SAR, China（香港科技大学）；SEU Jiangsu, China（江苏大学）；HKUST(GZ) Guangzhou, China（香港科技大学（广州））；Zhipu AI Beijing, China（智谱AI）；HKUST(GZ), HKUST Guangzhou, China（香港科技大学（广州）、香港科技大学）
Supervised Fine Tuning of Large Language Models for Domain Specific Knowledge Graph Construction:A Case Study on Hunan's Historical Celebrities
College of Information Science and Engineering（信息科学与工程学院）；Hunan Provincial Key Laboratory of Philosophy and Social Sciences of Yuelushan Cultural and Digital Communication (Artificial Intelligence and International Communication AIIC)（湖南省级哲学社会科学岳麓文化与数字传播重点实验室（人工智能与国际传播AIIC））；College of Computer Science and Electronic Engineering（计算机科学与电子工程学院）
Domain-Adapted Pre-trained Language Models for Implicit Information Extraction in Crash Narratives
Department of Technology, Management and Economics, Technical University of Denmark（技术、管理与经济系，丹麦技术大学）；Department of Mechanics and Maritime Sciences, Chalmers University of Technology（机械与航海科学系，查尔姆斯理工大学）；Department of Computer Science and Engineering, Chalmers University of Technology（计算机科学与工程系，查尔姆斯理工大学）
Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；University Of Electronic Science And Technology Of China（电子科技大学）
有间隔的句子，如Paul likes coffee and Mary tea，缺少一个显性谓词来表示两个或多个论元之间的关系。这样的句子的表面句法表示通常由解析器产生得很差，并且即使正确，也不能很好地适合于下游自然语言理解任务，例如通常被设计为从具有规范子句结构的句子中提取信息的关系抽取。在本文中，我们提出了两种方法来解析到一个通用的消隐图表示，显式编码的省略材料与额外的节点和边缘。我们发现，这两种方法可以重建省略材料的依赖树，具有高精度时，解析器正确预测存在的差距。我们进一步证明，我们的方法之一，可以适用于其他语言的基础上对瑞典语的案例研究。
End-to-end Named Entity Recognition and Relation Extraction using Pre-trained Language Models
University of Toronto（多伦多大学）；The Donnelly Centre（唐纳利中心）；Vector Institute（矢量研究所）；University Health Network（大学健康网络）；Semantic Health（语义健康公司）；Peter Munk Cardiac Center（彼得·蒙克心脏中心）
Learning the grammar of drug prescription: recurrent neural network grammars for medication information extraction in clinical texts
CHU Necker, AP-HP（巴黎公共医疗救助机构内克尔大学医院）；INSERM UMR-S 872（法国国家健康与医学研究院 UMR-S 872）；Sorbonne Paris Cité, Faculté de Médecine（索邦巴黎西岱大学医学院）；Université de Paris（巴黎大学）
