User profiles for Defne Circi

Defne Circi

Graduate Student, Duke University
Verified email at duke.edu
Cited by 233

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

…, S Bringuier, LC Brinson, K Choudhary, D Circi… - Digital discovery, 2023 - pubs.rsc.org
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. …

How well do large language models understand tables in materials science?

D Circi, G Khalighinejad, A Chen, B Dhingra… - Integrating Materials and …, 2024 - Springer
Advances in materials science require leveraging past findings and data from the vast
published literature. While some materials data repositories are being built, they typically rely on …

Phylogenetic analysis of SARS-CoV-2 genomes in Turkey

O Adebali, A Bircan, D Circi, B İşlek… - Turkish Journal of …, 2020 - journals.tubitak.gov.tr
COVID-19 has effectively spread worldwide. As of May 2020, Turkey is among the top ten
countries with the most cases. A comprehensive genomic characterization of the virus isolates …

The mutation profile of SARS-CoV-2 is primarily shaped by the host antiviral defense

C Azgari, Z Kilinc, B Turhan, D Circi, O Adebali - Viruses, 2021 - mdpi.com
Understanding SARS-CoV-2 evolution is a fundamental effort in coping with the COVID-19
pandemic. The virus genomes have been broadly evolving due to the high number of …

Extracting polymer nanocomposite samples from full-length documents

G Khalighinejad, D Circi, LC Brinson… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

Evaluating morphological compositional generalization in large language models

M Ismayilzada, D Circi, J Sälevä, H Sirin… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) have demonstrated significant progress in various natural
language generation and understanding tasks. However, their linguistic generalization …

[PDF][PDF] POLLYDARTON–NLP-DRIVEN DATA CURATION FOR POLYMER NANOCOMPOSITE DATA RESOURCE

J Axelrod, D Circi, L Cooper, T Lilly, S Miki - logan-cooper.com
Materials science researchers spend significant time sifting through articles to identify relevant
methods and properties that could aid their own research. We can model this challenge …

Reflections from the 2024 large language model (llm) hackathon for applications in materials science and chemistry

…, A Canalicchio, V Chen, Y Chiang, D Circi… - arXiv preprint arXiv …, 2024 - arxiv.org
Here, we present the outcomes from the second Large Language Model (LLM) Hackathon
for Applications in Materials Science and Chemistry, which engaged participants across …

Retrieval of synthesis parameters of polymer nanocomposites using llms

D Circi, G Khalighinejad, S Badhwar… - AI for accelerated …, 2023 - openreview.net
Automated materials synthesis requires historical data, but extracting detailed data and
metadata from publications is challenging. We developed initial strategies for using large …

Extracting Materials Science Data from Scientific Tables

D Circi, G Khalighinejad, A Chen… - ACL 2024 Workshop …, 2024 - openreview.net
Advances in materials science depend on leveraging data from the vast published literature.
Extracting detailed data and metadata from these publications is challenging, leading …