2024年大型語言模型（LLM）黑客松在材料科學和化學應用領域的反思

Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

November 20, 2024

作者: Yoel Zimmermann, Adib Bazgir, Zartashia Afzal, Fariha Agbere, Qianxiang Ai, Nawaf Alampara, Alexander Al-Feghali, Mehrad Ansari, Dmytro Antypov, Amro Aswad, Jiaru Bai, Viktoriia Baibakova, Devi Dutta Biswajeet, Erik Bitzek, Joshua D. Bocarsly, Anna Borisova, Andres M Bran, L. Catherine Brinson, Marcel Moran Calderon, Alessandro Canalicchio, Victor Chen, Yuan Chiang, Defne Circi, Benjamin Charmes, Vikrant Chaudhary, Zizhang Chen, Min-Hsueh Chiu, Judith Clymo, Kedar Dabhadkar, Nathan Daelman, Archit Datar, Matthew L. Evans, Maryam Ghazizade Fard, Giuseppe Fisicaro, Abhijeet Sadashiv Gangan, Janine George, Jose D. Cojal Gonzalez, Michael Götte, Ankur K. Gupta, Hassan Harb, Pengyu Hong, Abdelrahman Ibrahim, Ahmed Ilyas, Alishba Imran, Kevin Ishimwe, Ramsey Issa, Kevin Maik Jablonka, Colin Jones, Tyler R. Josephson, Greg Juhasz, Sarthak Kapoor, Rongda Kang, Ghazal Khalighinejad, Sartaaj Khan, Sascha Klawohn, Suneel Kuman, Alvin Noe Ladines, Sarom Leang, Magdalena Lederbauer, Sheng-Lun Mark Liao, Hao Liu, Xuefeng Liu, Stanley Lo, Sandeep Madireddy, Piyush Ranjan Maharana, Shagun Maheshwari, Soroush Mahjoubi, José A. Márquez, Rob Mills, Trupti Mohanty, Bernadette Mohr, Seyed Mohamad Moosavi, Alexander Moßhammer, Amirhossein D. Naghdi, Aakash Naik, Oleksandr Narykov, Hampus Näsström, Xuan Vu Nguyen, Xinyi Ni, Dana O'Connor, Teslim Olayiwola, Federico Ottomano, Aleyna Beste Ozhan, Sebastian Pagel, Chiku Parida, Jaehee Park, Vraj Patel, Elena Patyukova, Martin Hoffmann Petersen, Luis Pinto, José M. Pizarro, Dieter Plessers, Tapashree Pradhan, Utkarsh Pratiush, Charishma Puli, Andrew Qin, Mahyar Rajabi, Francesco Ricci, Elliot Risch, Martiño Ríos-García, Aritra Roy, Tehseen Rug, Hasan M Sayeed, Markus Scheidgen, Mara Schilling-Wilhelmi, Marcel Schloz, Fabian Schöppach, Julia Schumann, Philippe Schwaller, Marcus Schwarting, Samiha Sharlin, Kevin Shen, Jiale Shi, Pradip Si, Jennifer D'Souza, Taylor Sparks, Suraj Sudhakar, Leopold Talirz, Dandan Tang, Olga Taran, Carla Terboven, Mark Tropin, Anastasiia Tsymbal, Katharina Ueltzen, Pablo Andres Unzueta, Archit Vasan, Tirtha Vinchurkar, Trung Vo, Gabriel Vogel, Christoph Völker, Jan Weinreich, Faradawn Yang, Mohd Zaki, Chi Zhang, Sylvester Zhang, Weijie Zhang, Ruijie Zhu, Shang Zhu, Jan Janssen, Ian Foster, Ben Blaiszik

cs.AI

摘要

在這裡，我們介紹了第二屆大型語言模型（LLM）應用於材料科學和化學的黑客松的成果，吸引了來自全球混合地點的參與者，共收到34個團隊提交。這些提交涵蓋了七個主要應用領域，展示了LLM在（1）分子和材料性質預測；（2）分子和材料設計；（3）自動化和新穎界面；（4）科學交流和教育；（5）研究數據管理和自動化；（6）假設生成和評估；以及（7）從科學文獻中提取和推理的多樣效用。每個團隊提交都在摘要表中呈現，附有代碼鏈接和簡短論文。除了團隊成果，我們還討論了黑客松活動及其混合形式，包括多個實體中心在多倫多、蒙特利爾、舊金山、柏林、洛桑和東京，以及一個全球在線中心以促進當地和虛擬協作。整體而言，該活動突顯了自上一屆黑客松以來LLM功能的顯著改進，表明LLM在材料科學和化學研究應用中持續擴展。這些成果展示了LLM的雙重效用，既是多功能模型用於各種機器學習任務，也是快速原型化科學研究自定義應用的平台。

English

Here, we present the outcomes from the second Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry, which engaged participants across global hybrid locations, resulting in 34 team submissions. The submissions spanned seven key application areas and demonstrated the diverse utility of LLMs for applications in (1) molecular and material property prediction; (2) molecular and material design; (3) automation and novel interfaces; (4) scientific communication and education; (5) research data management and automation; (6) hypothesis generation and evaluation; and (7) knowledge extraction and reasoning from scientific literature. Each team submission is presented in a summary table with links to the code and as brief papers in the appendix. Beyond team results, we discuss the hackathon event and its hybrid format, which included physical hubs in Toronto, Montreal, San Francisco, Berlin, Lausanne, and Tokyo, alongside a global online hub to enable local and virtual collaboration. Overall, the event highlighted significant improvements in LLM capabilities since the previous year's hackathon, suggesting continued expansion of LLMs for applications in materials science and chemistry research. These outcomes demonstrate the dual utility of LLMs as both multipurpose models for diverse machine learning tasks and platforms for rapid prototyping custom applications in scientific research.