More Like this

1. LCGC and ACS Subdivision on Chromatography and Separations Chemistry Survey 2023: What Skills Do New Analytical Chemistry Employees Need?

   https://doi.org/10.56530/lcgc.na.uc7884m3  

   Grinias, James; Smith, Trevor; Kovarik, Michelle (August 2023, LCGC North America)

   For this year’s career issue, LCGC North America teamed up with the American Chemical Society Subdivision on Chromatography and Separations Chemistry to ask the analytical chemistry community what skills new employees in the field need to succeed. In this report, we analyze the survey results and explore how they can inform the future of analytical chemistry curriculum development. 

   more » « less
2. What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks

   Guo, T; Guo, K; Nan, B; Liang, Z; Guo, Z; Chawla, NV; Wiest, O; Zhang, X (December 2023, 37th Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks.)

   Large Language Models (LLMs) with strong abilities in natural language processing tasks have emerged and have been applied in various kinds of areas such as science, finance and software engineering. However, the capability of LLMs to advance the field of chemistry remains unclear. In this paper, rather than pursuing state-of-the-art performance, we aim to evaluate capabilities of LLMs in a wide range of tasks across the chemistry domain. We identify three key chemistryrelated capabilities including understanding, reasoning and explaining to explore in LLMs and establish a benchmark containing eight chemistry tasks. Our analysis draws on widely recognized datasets facilitating a broad exploration of the capacities of LLMs within the context of practical chemistry. Five LLMs (GPT-4, GPT-3.5, Davinci-003, Llama and Galactica) are evaluated for each chemistry task in zero-shot and few-shot in-context learning settings with carefully selected demonstration examples and specially crafted prompts. Our investigation found that GPT-4 outperformed other models and LLMs exhibit different competitive levels in eight chemistry tasks. In addition to the key findings from the comprehensive benchmark analysis, our work provides insights into the limitation of current LLMs and the impact of in-context learning settings on LLMs’ performance across various chemistry tasks. The code and datasets used in this study are available at https://github.com/ChemFoundationModels/ChemLLMBench. 

   more » « less
3. How Do Inorganic Students Represent Molecular Orbitals? A Multi-Institutional Study from the Foundation-Level Inorganic Chemistry Course

   https://doi.org/10.1021/acs.jchemed.3c00823  

   Reisner, Barbara A.; Kinkaid, Melissa M.; Pratt, Justin M.; Bentley, Anne K.; Stewart, Joanne L.; Smith, Sheila R.; Raker, Jeffrey R.; Lin, Shirley (January 2024, Journal of Chemical Education)
4. What Do Martians Do at Night?

   https://doi.org/10.52400/ECUK9571  

   Benner, Steven (November 2023, blog post)
5. What Do You Do With an Idea?

   https://doi.org/10.5951/MTLT.2023.0366  

   Krause, Gladys H; Finchum, Caroline Utne; Borja, Maria-Emilia (September 2024, Mathematics Teacher: Learning and Teaching PK-12)

   In a mathematics class where students are encouraged to freely share ideas, the room brims with diverse thoughts. How do students and teachers use them? Let’s follow a group of multilingual students and teachers to see what they did with an idea! 

   more » « less