Promoting Women's Participation in STEM through a Digital Tool Based on Large Language Models (LLM)
DOI:
https://doi.org/10.47756/aihc.y9i1.183Keywords:
STEM, Women, Large Language Model, Gender Bias, Vocational Guidance Agent, Growth Mindset Supportive LanguageAbstract
Despite the growing demand for STEM education (Science, Technology, Engineering, and Mathematics), a gender gap persists, influenced by stereotypes, lack of confidence in mathematical abilities, and inadequate vocational guidance. Practical strategies to increase women's participation in STEM include technological interventions. A vocational guidance agent based on Large Language Models (LLMs), specifically designed for women can enhance STEM education by providing personalized learning and targeted guidance, thus fostering greater female participation in these fields.
However, LLMs may perpetuate biases due to their training on human-generated texts. To address this issue, we propose the design of a digital tool based on LLMs, exploring personalization techniques and improvements in these systems. The agent is envisioned to incorporate Growth Mindset Supportive Language (GMSL) to foster a growth mindset, challenge gender stereotypes, and support women's STEM identity.
Downloads
References
Graciela Rojas Montemayor, Laura Segura Guzmán, & Gina Andrade Baena. (2023). Informe sobre la brecha de género en STEM en México. Movimiento STEM+, OIT, y UNICEF. Recuperado de
Darraz, M. C. F., Guerrero, G. M., & Pincheira, D. A. Transformar las desigualdades educativas: El rol del género en la orientación vocacional. Recuperado de
Microsoft. (2018). Closing the STEM gap: Why STEM classes and careers still lack girls and what we can do about it. Microsoft Corporation. Recuperado de
https://query.prod.cms.rt.microsoft.com/cms/api/am/binary/RE1UMWz.
Prieto-Rodriguez, E., Sincock, K., & Blackmore, K. (2020). STEM initiatives matter: Results from a systematic review of secondary school interventions for girls. International Journal of Science Education, 42(7), 1144-1161. DOI: https://doi.org/10.1080/09500693.2020.1749909
Dominguez, A., Meléndez-Anzures, F., Tejeda, S., Zavala, G., Verdugo-Castro, S., García-Holgado, A., & Sanjakdar, F. Use of technology to empower and connect women in STEM. Recuperado de
Stoeger, H., Debatin, T., Heilemann, M., & Ziegler, A. (2019). Online mentoring for talented girls in STEM: The role of relationship quality and changes in learning environments in explaining mentoring success. New Directions for Child and Adolescent Development, 2019(168), 75-99. DOI: https://doi.org/10.1002/cad.20320
Demszky, D., Yang, D., Yeager, D. S., Bryan, C. J., Clapper, M., Chandhok, S., ... & Pennebaker, J. W. (2023). Using large language models in psychology. Nature Reviews Psychology, 2(11), 688-701 DOI: https://doi.org/10.1038/s44159-023-00241-5
Ovadia, O., Brief, M., Mishaeli, M., & Elisha, O. (2023). Fine-tuning or retrieval? comparing knowledge injection in llms. arXiv preprint arXiv:2312.05934. DOI: https://doi.org/10.18653/v1/2024.emnlp-main.15
Oymak, S., Rawat, A.S., Soltanolkotabi, M. & Thrampoulidis, C.. (2023). On the Role of Attention in Prompt-tuning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:26724-26768. Recuperado de https://proceedings.mlr.press/v202/oymak23a.html.
Vijay Kumar, A. B. (2024). Multi-Agent systems are LLM applications that are changing the automation landscape with intelligent bots. Medium. Recuperado de https://abvijaykumar.medium.com/multi-agent-architectures-e09c53c7fe0d.
Huang, J., Li, K., & Yehdego, D. (2024). Evaluating Large Language Model (LLM) systems: Metrics, challenges, and best practices. Data Science at Microsoft. Recuperado de
Handa, K., Clapper, M., Boyle, J., Wang, R. E., Yang, D., Yeager, D. S., & Demszky, D. (2023). " Mistakes Help Us Grow": Facilitating and Evaluating Growth Mindset Supportive Language in Classrooms. arXiv preprint arXiv:2310.10637. DOI: https://doi.org/10.18653/v1/2023.emnlp-main.549
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
AMexIHC make every effort to ensure the accuracy and rigour of all the information (the "Content") contained in out publications. However, AMexIHC and our representatives make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by AMexIHC. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information.
