The ADAIO System at the BEA-2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues

06/08/2023
by   Adaeze Adigwe, et al.
0

This paper presents the ADAIO team's system entry in the Building Educational Applications (BEA) 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues. The task aims to assess the performance of state-of-the-art generative models as AI teachers in producing suitable responses within a student-teacher dialogue. Our system comprises evaluating various baseline models using OpenAI GPT-3 and designing diverse prompts to prompt the OpenAI models for teacher response generation. After the challenge, our system achieved second place by employing a few-shot prompt-based approach with the OpenAI text-davinci-003 model. The results highlight the few-shot learning capabilities of large-language models, particularly OpenAI's GPT-3, in the role of AI teachers.

READ FULL TEXT
research
06/12/2023

The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues

This paper describes the results of the first shared task on the generat...
research
07/09/2023

Assessing the efficacy of large language models in generating accurate teacher responses

(Tack et al., 2023) organized the shared task hosted by the 18th Worksho...
research
06/18/2023

Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy

Educational chatbots come with a promise of interactive and personalized...
research
06/05/2023

Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction

Coaching, which involves classroom observation and expert feedback, is a...
research
07/06/2023

Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment

Human communication often involves information gaps between the interloc...
research
05/16/2022

The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues

How can we test whether state-of-the-art generative models, such as Blen...
research
05/31/2023

Scaling Evidence-based Instructional Design Expertise through Large Language Models

This paper presents a comprehensive exploration of leveraging Large Lang...

Please sign up or login with your details

Forgot password? Click here to reset