Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2306.05360 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929303894097920 |
|---|---|
| author | Adigwe, Adaeze Yuan, Zheng |
| author_facet | Adigwe, Adaeze Yuan, Zheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_05360 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | The ADAIO System at the BEA-2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues Adigwe, Adaeze Yuan, Zheng Computation and Language Artificial Intelligence Computers and Society 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. |
| title | The ADAIO System at the BEA-2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2306.05360 |