Artificial intelligence’s (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. However, the ensuing excitement has led to negative sentiments, even as AI methods demonstrate remarkable contributions (e.g. in health and genetics). A key factor contributing to this sentiment is the misleading perception that LLMs can effortlessly provide solutions across domains, ignoring their limitations such as hallucinations and reasoning constraints. Acknowledging AI fallibility is crucial to address the impact of dogmatic overconfidence in possibly erroneous suggestions generated by LLMs. At the same time, it can reduce fear and other negative attitudes toward AI. This necessitates comprehensive AI literacy interventions that educate the public about LLM constraints and effective usage techniques, i.e. prompting strategies. With this aim, a pilot educational intervention was performed in a high school with 21 students. It involved presenting high-level concepts about intelligence, AI, and LLMs, followed by practical exercises involving ChatGPT in creating natural educational conversations and applying established prompting strategies. Encouraging preliminary results emerged, including high appreciation of the activity, improved interaction quality with the LLM, reduced negative AI sentiments, and a better grasp of limitations, specifically unreliability, limited understanding of commands leading to unsatisfactory responses, and limited presentation flexibility. Our aim is to explore AI acceptance factors and refine this approach for more controlled future studies.
Learning to Prompt in the Classroom to Understand AI Limits: A Pilot Study / E. Theophilou, C. Koyutürk, M. Yavari, S. Bursic, G. Donabauer, A. Telari, A. Testa, R. Boiano, D. Hernandez-Leo, M. Ruskov, D. Taibi, A. Gabbiadini, D. Ognibene (LECTURE NOTES IN COMPUTER SCIENCE). - In: AIxIA 2023 – Advances in Artificial Intelligence / [a cura di] Roberto Basili, Domenico Lembo, Carla Limongelli, Andrea Orlandini. - Prima edizione. - Cham : Springer, 2023. - ISBN 9783031475467. - pp. 481-496 (( Intervento presentato al 22. convegno International Conference of the Italian Association for Artificial Intelligence, AIxIA tenutosi a Roma : 6-9 Novembre nel 2023 [10.1007/978-3-031-47546-7_33].
Learning to Prompt in the Classroom to Understand AI Limits: A Pilot Study
S. Bursic;M. Ruskov;
2023
Abstract
Artificial intelligence’s (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. However, the ensuing excitement has led to negative sentiments, even as AI methods demonstrate remarkable contributions (e.g. in health and genetics). A key factor contributing to this sentiment is the misleading perception that LLMs can effortlessly provide solutions across domains, ignoring their limitations such as hallucinations and reasoning constraints. Acknowledging AI fallibility is crucial to address the impact of dogmatic overconfidence in possibly erroneous suggestions generated by LLMs. At the same time, it can reduce fear and other negative attitudes toward AI. This necessitates comprehensive AI literacy interventions that educate the public about LLM constraints and effective usage techniques, i.e. prompting strategies. With this aim, a pilot educational intervention was performed in a high school with 21 students. It involved presenting high-level concepts about intelligence, AI, and LLMs, followed by practical exercises involving ChatGPT in creating natural educational conversations and applying established prompting strategies. Encouraging preliminary results emerged, including high appreciation of the activity, improved interaction quality with the LLM, reduced negative AI sentiments, and a better grasp of limitations, specifically unreliability, limited understanding of commands leading to unsatisfactory responses, and limited presentation flexibility. Our aim is to explore AI acceptance factors and refine this approach for more controlled future studies.File | Dimensione | Formato | |
---|---|---|---|
2307.01540.pdf
embargo fino al 02/11/2024
Descrizione: Book Chapter
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
763.41 kB
Formato
Adobe PDF
|
763.41 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
978-3-031-47546-7_33.pdf
accesso riservato
Descrizione: Chapter Book
Tipologia:
Publisher's version/PDF
Dimensione
387.39 kB
Formato
Adobe PDF
|
387.39 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.