Extracting Polymer Nanocomposite Samples from Full-Length Documents

arXiv:2403.00260v1 Announce Type: new
Abstract: 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 …

abstract arxiv challenge complexity cs.cl documents information language language models large language large language models lies lists llms materials materials science nature paper papers research research papers sample samples science text type