Search

Your search keyword '"Circi, Defne"' showing total 4 results
Start Over Author "Circi, Defne"
4 results on '"Circi, Defne"'

1. Extracting Polymer Nanocomposite Samples from Full-Length Documents

Author

Khalighinejad, Ghazal, Circi, Defne, Brinson, L. C., and Dhingra, Bhuwan

Subjects
Computer Science - Computation and Language
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 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.

Published
2024

3. 14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon

Author

Jablonka, Kevin Maik, Ai, Qianxiang, Al-Feghali, Alexander, Badhwar, Shruti, Bocarsly, Joshua D, Bran, Andres M, Bringuier, Stefan, Brinson, L Catherine, Choudhary, Kamal, Circi, Defne, Cox, Sam, de Jong, Wibe A, Evans, Matthew L, Gastellu, Nicolas, Genzling, Jerome, Gil, María Victoria, Gupta, Ankur K, Hong, Zhi, Imran, Alishba, Kruschwitz, Sabine, Labarre, Anne, Lála, Jakub, Liu, Tao, Ma, Steven, Majumdar, Sauradeep, Merz, Garrett W, Moitessier, Nicolas, Moubarak, Elias, Mouriño, Beatriz, Pelkie, Brenden, Pieler, Michael, Ramos, Mayk Caldas, Ranković, Bojana, Rodriques, Samuel G, Sanders, Jacob N, Schwaller, Philippe, Schwarting, Marcus, Shi, Jiale, Smit, Berend, Smith, Ben E, Van Herck, Joren, Völker, Christoph, Ward, Logan, Warren, Sean, Weiser, Benjamin, Zhang, Sylvester, Zhang, Xiaoqi, Zia, Ghezal Ahmad, Scourtas, Aristana, Schmidt, KJ, Foster, Ian, White, Andrew D, and Blaiszik, Ben

Subjects
Macromolecular and Materials Chemistry, Chemical Sciences
Abstract

Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, we organized a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications. The diverse topics and the fact that working prototypes could be generated in less than two days highlight that LLMs will profoundly impact the future of our fields. The rich collection of ideas and projects also indicates that the applications of LLMs are not limited to materials science and chemistry but offer potential benefits to a wide range of scientific disciplines.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results