Teknologia kemian opetuksessa

ChatGPT tarvitsee myös kemian opettajan

2023-12-21T12:42:10+02:00

Artikkeli englanniksi.

AI and ChatGPT technology have the potential to revolutionize the education sector, and this study aimed to evaluate if prompt formats, response consistency, and reliability of ChatGPT responses could help colleges make the most of this technology. The results of this study can guide future AI and ChatGPT implementations and ensure they are used to their fullest potential. The data does not demonstrate a statistically significant difference between multiple-choice and free response prompt formats. Neither format achieved scores higher than 37%, and testing different locations did not improve scores. Interestingly, ChatGPT's free version provides accurate responses to discipline-specific questions that contain information from unrelated topics, improving its accuracy over the free response questions. However, it's important to remember that while ChatGPT can identify the correct answer within a given context, it may not be able to tell if the answer it chooses is correct computationally or through analysis.

Viittaaminen: Leon, A., & Vidhani, D. (2023). ChatGPT Needs a Chemistry Tutor Too. ChemRxiv. https://doi.org/10.26434/chemrxiv-2023-qpzx3

Laajojen kielimallien kyvyt lukion kemian opetuksessa

2023-12-21T13:00:08+02:00

Artikkeli englanniksi.

This study evaluates the potential and challenges of large langue models (LLMs) for education in chemistry. Specifically, we analyze the performance of two state -of-the art of LLMs, ChatGPT and Microsoft Bing AI Chat, on a quiz dataset consisting of 200 multiple-choice questions in chemistry at the high school level. The results show that ChatGPT and Microsoft Bing AI Chat have limitations in answering questions at the application and high application levels. We also compare the scores of the LLMs models with Vietnamese students, indicating that their performance is still lower than the ability of Vietnamese students. The findings suggest that LLMs have great potential in assisting learning and teaching, but further development is needed to improve their ability to solve complex questions at the high application level.

Viittaaminen: Xuan-Quy, D., Ngoc-Bich, L., The-Duy, V., Bac-Bien, N., & Xuan-Dung, P. (2023). LLMs’ Capabilities at the High School Level in Chemistry: Cases of ChatGPT and Microsoft Bing Chat. ChemRxiv. https://doi.org/10.26434/chemrxiv-2023-kxxpd

Kuratoidun chatbotin kehittäminen kemian oppimisen tueksi

2023-12-21T12:36:05+02:00

Artikkeli englanniksi.

This report details the development of an interactive web-based chatbot to curate content for writing about chemistry in context. Using machine learning, the chatbot undergoes training through the phrases inputted by the developer and its users to create stronger connections to different modules. Discussed herein are the development of the decision tree, the chatbot’s components, and results from the initial implementation in a large lecture general chemistry classroom.

Viittaaminen: Lolinco, A., & Holme, T. (2023). Developing a curated chatbot as an exploratory communication tool for chemistry learning. ChemRxiv. https://doi.org/10.26434/chemrxiv-2023-p9css

Mitä suuret kielimallit voivat tehdä kemiassa?

2023-12-21T11:46:38+02:00

Artikkeli englanniksi.

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 chemistry-related 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 this https URL.

Viittaaminen: Guo, T., Guo, K., Nan, B., Liang, Z., Guo, Z., Chawla, N. V., Wiest, O., & Zhang, X. (2023). What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks (arXiv:2305.18365). arXiv. https://doi.org/10.48550/arXiv.2305.18365

Generatiivisen tekoälyn käyttö kemian opetuksen tutkimuksessa:

2023-12-21T13:07:19+02:00

Artikkeli englanniksi.

Generative artificial intelligence (GenAI) has the potential to drastically alter how we teach and conduct research in chemistry education. There have been many reports on the potential uses, limitations, and considerations for GenAI tools in teaching and learning, but there have been fewer discussions of how such tools could be leveraged in educational research, including in chemistry education research. GenAI tools can be used to facilitate and support researchers in every stage of traditional educational research projects (e.g. conducting literature reviews, designing research questions and methods, communicating results). However, these tools also have existing limitations that researchers must be aware of prior to and during use. In this research commentary, we share insights on how chemistry education researchers can use GenAI tools in their work ethically. We also share how GenAI tools can be leveraged to improve accessibility and equity in research.

Viittaaminen: Deng, J. M., Lalani, Z., McDermaid, L. A., & Szozda, A. R. (2023). Using generative artificial intelligence in chemistry education research: Prioritizing ethical use and accessibility. ChemRxiv. https://doi.org/10.26434/chemrxiv-2023-24zfl-v2

Kemian oppimisen tehostaminen ChatGPT:llä, Bing Chatilla, Bardilla ja Claudella ajatteluagentteina

2023-12-21T11:30:40+02:00

Artikkeli englanniksi.

This research delves into the comparative advantages of Generative AI chatbots (GenAIbots) -- ChatGPT, Bing Chat, Bard, and Claude -- in the context of Chemistry education, framed within a constructivist perspective. Our primary objective was to identify which of these four AI tools is more effective for enhancing Chemistry learning. Employing a single-case study approach, we scrutinised interaction logs between the AI systems and a simulated student persona during Chemistry learning simulations, incorporating Content Analysis methodology to delve deeper into the discourse. Our findings underscore these tools' potential as "agents-to-think-with", enhancing critical thinking, problem-solving, comprehension, creativity, and tailored learning. Especially noteworthy is their ability to stimulate learners through Socratic-like questioning, aligning with constructionist principles. The research emphasises the pivotal role of prompt crafting to coax desired responses from GenAIbots, engendering iterative reflections. It also highlights the need for robust educator training to infuse these technologies into educational settings. Conclusively, while ChatGPT, Bing Chat, Bard, and Claude are poised to enrich Chemistry education by fostering dynamic, inclusive learning experiences, ChatGPT stood out, decisively surpassing Bing Chat in its performance. Bard and Claude trailed closely, with all three showcasing a more in-depth, precise, and nuanced understanding, underscoring ChatGPT's adeptness at contextual comprehension.

Viittaaminen: Santos, R. P. dos. (2023). Enhancing Chemistry Learning with ChatGPT, Bing Chat, Bard, and Claude as Agents-to-Think-With: A Comparative Case Study (arXiv:2311.00709). arXiv. https://doi.org/10.48550/arXiv.2311.00709

Tekoälytutkijan nousu

2023-12-21T12:50:58+02:00

Artikkeli englanniksi.

Digital twin laboratories, accessible via the use of low-cost and portable virtual reality (VR) headsets, have emerged as an immensely powerful tool for chemical education and research collaboration. Having an immersive environment identical to that of a laboratory can provide scientists with a unique platform in which to plan future experiments, conduct laboratory tours, and train on specialist equipment. However, what digital twin laboratories currently lack is on-hand support of co-workers to assist with tasks such as locating chemicals, aiding with machine set-up, and issuing reminders regarding local laboratory health and safety rules Here we show how this key gap can be overcome with the use of knowledge-loaded Chat-GPT avatars in VR. We trained three different chat avatars to perform specialist functions crucial to working in a laboratory and obtained accurate and useful responses in up to 95% of cases, using a range of evaluation metrics including Human Evaluation, Set-Based F1 Scoring, and BERTScore. Our findings demonstrate the vast potential of this technology in harnessing the capabilities of AI assistants for scientists and enhancing immersive digital twin environments within VR settings.

Cite: Taylor, M., Muwaffak, Z., Penny, M., Szulc, B., Brown, S., Merritt, A., & Hilton, S. (2023). The Rise of the AI Scientist: Unleashing the Potential of Chat-GPT Powered Avatars in Virtual Reality Digital-twin Laboratories. ChemRxiv. https://doi.org/10.26434/chemrxiv-2023-t4vg7

Tekoäly-chatbotit kemiallisen informaation etsimisessä

2023-12-21T11:10:07+02:00

Artikkeli tarjolla vain englanniksi.

Artificial intelligence (AI) chatbots are the latest advance in information technology. They are next-word predictors built on large language models (LLM) that offer the possibility to process and generate information. In this theoretical article, we provide educational insights of the possibilities and challenges of educational usage of AI chatbots. The insights were produced in the context of chemical information-seeking activities designed for chemistry teacher education. The analysis was conducted via a SWOT approach using technological pedagogical content knowledge framework (TPACK) to improve the accuracy. The analysis revealed several internal and external possibilities and challenges. The key insight is that AI chatbots will change the way people interact with information. For example, they enable the building of personal learning environments with ubiquitous access to information and AI tutoring. Their ability to support chemistry learning is impressive. However, processing of chemical information reveals the limitations of current AI chatbots not being able to process multimodal chemical information. There are also ethical issues to address. Despite the benefits, wider educational adoption of AI chatbots will take time. The obstacles hindering the adoption of AI chatbots can be removed, for example, through integrating LLMs to curricula, focusing on open-source solutions, and training teachers with modern information literacy skills. This research presents theory-grounded examples of how to support the development of modern information literacy skills in chemistry teacher education. Based on the conducted analysis, we predict that AI chatbots will be a major technological change agent towards inclusive and equitable quality lifelong learning for all.

Viittaaminen: Pernaa, J.; Ikävalko, T.; Takala, A.; Vuorio, E.; Pesonen, R.; Haatainen, O. Artificial Intelligence Chatbots in Chemical Information Seeking: Educational Insights through a SWOT analysis. Preprints 2023, 2023121066. https://doi.org/10.20944/preprints202312.1066.v1