GPT-3-Driven Pedagogical Agents to Train Children’s Curious Question-Asking Skills

نویسندگان

چکیده

In order to train children's ability ask curiosity-driven questions, previous research has explored designing specific exercises relying on providing semantic and linguistic cues help formulate such questions. But despite showing pedagogical efficiency, this method is still limited as it relies generating the said by hand, which can be a very costly process. context, we propose leverage advances in natural language processing field (NLP) investigate efficiency of using large model (LLM) for automating production content curious question-asking (QA) training. We study "prompt-based" that consists explaining task LLM text. evaluate output human experts annotations comparisons with hand-generated content. Results suggested indeed relevance usefulness also conduct primary school (75 children aged 9-10), where QA performance when having compare 3 types : 1) proposes "closed" leading predefined questions; 2) GPT-3-generated same type cues; 3) "open" several possible see similar between two trainings (showing scalability approach GPT-3), better one participants These results suggest LLMs support more prompting affords usability teachers other users not specialists AI techniques. Furthermore, show open-ended may suitable training skills.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Using Cognitive Agents to Train Negotiation Skills

Training negotiation is difficult because it is a complex, dynamic activity that involves multiple parties. It is often not clear how to create situations in which students can practice negotiation or how to measure students' progress. Some have begun to address these issues by creating artificial software agents with which students can train. These agents have the advantage that they can be "r...

متن کامل

Asking the Right Question

For instance, enthusiasts of object-oriented programming were initially keen to promote the value of hierarchical models. Only later did experimental evidence reveal that deep hierarchies are more error prone than shallow ones. In contrast, medical practice has changed dramatically during the last decade as a result of adopting an evidence-based paradigm. In the late ’80s and early ’90s, studie...

متن کامل

Question Asking During Tutoring

Whereas it is well documented that student question asking is infrequent in classroom environments, there is little research on questioning processes during tutoring. The present study investigated the questions asked in tutoring sessions on research methods (college students) and algebra (7th graders). Student questions were approximately 240 times as frequent in tutoring settings as classroom...

متن کامل

Asking the right question.

Rendell's most recent predecessor, Tom Ridge , illustrates the historical pattern. Who shall forget the constant allusions to "one-term Tom" that made the rounds of the state capitol during the end of his first year in 1995 and into his second year? Ridge had actually started his governorship with a successful special legislative session dealing with crime legislation and a tax cutting state bu...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: International Journal of Artificial Intelligence in Education

سال: 2023

ISSN: ['1560-4292', '1560-4306']

DOI: https://doi.org/10.1007/s40593-023-00340-7