Extracting Polymer Nanocomposite Samples from Full-Length Documents
This paper investigates the use of large language models (LLMs) for extracting sample lists of polymer nanocomposites (PNCs) from full-length materials science research papers. The challenge lies in the complex nature of PNC samples, which have numerous attributes scattered throughout the text. The complexity of annotating detailed information on PNCs limits the availability of data, making conventional document-level relation extraction techniques impractical due to the challenge in creating comprehensive named entity span annotations. To address this, we introduce a new benchmark and an evaluation technique for this task and explore different prompting strategies in a zero-shot manner. We also incorporate self-consistency to improve the performance. Our findings show that even advanced LLMs struggle to extract all of the samples from an article. Finally, we analyze the errors encountered in this process, categorizing them into three main challenges, and discuss potential strategies for future research to overcome them.
Code (1)
Tasks
Document-level Relation ExtractionRelation ExtractionSimilar Papers 제목 키워드 기반
A thermodynamically consistent physics-informed deep learning material model for short fiber/polymer nanocomposites
This work proposes a physics-informed deep learning (PIDL)-based constitutive model for investigating the viscoelastic-viscoplastic behavior of short fiber-reinforced nanoparticle-filled epoxies under various ambient con…
Deep LearningHaptic in-sensor computing device made of carbon nanotube-polydimethylsiloxane nanocomposites
The importance of haptic in-sensor computing devices has been increasing. In this study, we successfully fabricated a haptic sensor with a hierarchical structure via the sacrificial template method, using carbon nanotube…
Object RecognitionPolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literature
Scientific information extraction (SciIE), which aims to automatically extract information from scientific literature, is becoming more important than ever. However, there are no existing SciIE datasets for polymer mater…
ArticlesRelation Extraction3D scaffold with effective multidrug sequential release against bacteria biofilm
Bone infection is a feared complication following surgery or trauma that remains as an extremely difficult disease to deal with. So far, the outcome of therapy could be improved with the design of 3D implants, which comb…
The evolution of complexity and the transition to biochemical life
While modern physics and biology satisfactorily explain the passage from the Big Bang to the formation of Earth and the first cells to present-day life, respectively, the origins of biochemical life still remain an open …