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

Abdelghani, Rania; Wang, Yen-Hsiang; Yuan, Xingdi; Wang, Tong; Lucas, Pauline; Sauzéon, Hélène; Oudeyer, Pierre-Yves

doi:10.1007/s40593-023-00340-7

Cited by 44 publications

(11 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While there is some variability in how participants experience these activities, the general trend points to the beneficial role of ChatGPT in enhancing specific cognitive skills related to language learning. These tools simulate real-world language use and encourage collaborative learning, potentially transforming the landscape of language learning (Abdelghani et al, 2022). Pang (2022) and Grassini (2023) highlight the potential of integrating AI technologies such as ChatGPT into language instruction, emphasizing creating customized and adaptable learning environments tailored to individual student needs.…”

Section: Discussionmentioning

confidence: 99%

“…By nurturing informed decision-making regarding AI, learners can enhance their critical thinking and decision-making abilities. Language education is revolutionized by AI tools like ChatGPT, which offer personalized, adaptable, and captivating learning experiences that mirror real-life language usage and promote collaborative learning (Abdelghani et al, 2022). However, integrating AI into education must acknowledge the Arab World English Journal www.awej.org ISSN: 2229-9327 213 significance of addressing social and ethical concerns, including AI's fair and responsible utilization.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Empowering Language Learners’ Critical Thinking: Evaluating ChatGPT’s Role in English Course Implementation

Avsheniuk,

Lutsenko,

Svyrydiuk

et al. 2024

Preprint

View full text Add to dashboard Cite

This study investigates the influence of ChatGPT on critical thinking and English language learning within Ukrainian university English departments. Utilizing qualitative and quantitative methods, it involved 31 students and three language instructors in surveys and ChatGPT-assisted project-based activities. The significance of this study lies in its potential to guide the integration of AI tools in educational contexts, particularly in language learning. By examining the benefits and challenges of using ChatGPT, the study provides insights into how AI can support or hinder language learning and critical thinking. This is particularly relevant in the context of rapidly evolving educational technologies and the increasing use of AI in academic settings. In the spring semester of 2023, a research study was carried out involving students participating in a project-based activity using ChatGPT. The study comprised two main phases: initial survey, project completion, and evaluation. Quantitatively, it was found that 62% of students use ChatGPT weekly, underlining its role in their language studies. The results showed varied perspectives on its efficacy, especially in critical thinking, English skills development, and ethical considerations. Ethical and pedagogical issues were also significant, including concerns about the authenticity of AI responses, plagiarism risks, and AI dependency. Nevertheless, the potential advantages of ChatGPT, such as immediate language support and the promotion of learner independence, were acknowledged by students. The research concludes by recommending a careful integration of AI in language education.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Empowering Language Learners’ Critical Thinking: Evaluating ChatGPT’s Role in English Course Implementation

Avsheniuk,

Lutsenko,

Svyrydiuk

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, numerous researchers have endeavored to incorporate LLMs into educational technologies [51]. These adaptations have seen the utilization of LLMs in creating educational content [19,29], enhancing student engagement and interaction [1,7,88], and personalizing learning experiences [81]. For instance, LLMs have been used to generate children's narratives [4,35], some of which have even been sold publicly [64].…”

Section: Using Large Language Models For Child-facing Conversational ...mentioning

confidence: 99%

Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

Zhang,

Liu,

Ziska

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Figure 1: Interaction between a child and Mathemyths: demonstrating the system's ability to teach mathematical language through child-AI co-creative storytelling. Mathemyths provides open-ended questions to solicit how the child wishes the story should progress, on-the-fly feedback to acknowledge the child's responses, and co-creative story continuation with in-context explanations of math words. When the child needs additional support to continue the story, Mathemyths offers scaffolding through follow-up questions and "hint & rephrase" strategies.

show abstract

“…Studies considered precision and accuracy metrics conditioned on contexts to better quantify retrieval performance [9,21,22,23,24,25]. Researchers also used context divergence as a measure to assess the disparity between retrieved information and the user's intended meaning [26,27,28]. The evaluation included context-specific submetrics as part of standard test methodologies [29,2,30].…”

Section: Evaluation Of Contextual Relevancementioning

confidence: 99%

Adaptive Query Contextualization Algorithm for Enhanced Information Retrieval in Alpaca LLM

Kuo,

Huang,

Tsai

2023

Preprint

View full text Add to dashboard Cite

This study focused on the development and evaluation of an Adaptive Query Contextualization Algorithm (AQCA) within the Alpaca Large Language Model (LLM) framework. The AQCA was designed to enhance the model's capability in information retrieval by employing a novel context encoding methodology that dynamically adapted to multifaceted contextual signals derived from user search history and interaction patterns. The algorithm's efficacy was rigorously tested across various metrics, including Contextual Relevance Score (CRS), Word Prediction Accuracy (WPA), Information Retrieval Fidelity (IRF), and Response Coherence Measure (RCM). Significant improvements were observed in the augmented Alpaca LLM's performance, especially in complex scenarios such as metaphorical language understanding and domain-specific knowledge integration. Challenges related to scalability, adaptability to multilingual contexts, and integration with diverse LLM architectures were identified, emphasizing the need for continued research in these areas. The study concluded that while the AQCA marked a substantial advancement in LLMs for context-aware information retrieval, it also opened avenues for future innovations focusing on technical enhancements and ethical considerations.

show abstract

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

Cited by 44 publications

References 50 publications

Empowering Language Learners’ Critical Thinking: Evaluating ChatGPT’s Role in English Course Implementation

Empowering Language Learners’ Critical Thinking: Evaluating ChatGPT’s Role in English Course Implementation

Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

Adaptive Query Contextualization Algorithm for Enhanced Information Retrieval in Alpaca LLM

Contact Info

Product

Resources

About