# GPT-3-driven pedagogical agents for training children's curious question-asking skills

arXiv: https://arxiv.org/abs/2211.14228 · HTML: https://mlsanity.com/paper/2211.14228/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 79 references that are in the map.
- First posted on arXiv 25 Nov 2022.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation](https://mlsanity.com/paper/2106.03164/) (2021)
- [Reordering Examples Helps during Priming-based Few-Shot Learning](https://mlsanity.com/paper/2106.01751/) (2021)
- [Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation](https://mlsanity.com/paper/2209.11000/) (2022)
- [I Do Not Understand What I Cannot Define: Automatic Question Generation With Pedagogically-Driven Content Selection](https://mlsanity.com/paper/2110.04123/) (2021)
- [Conversational agents for fostering curiosity-driven learning in children](https://mlsanity.com/paper/2204.03546/) (2022)
- [Pedagogical Agents for Fostering Question-Asking Skills in Children](https://mlsanity.com/paper/2004.03472/) (2020)

## Built on by (most cited first, 29 of 29)

- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning](https://mlsanity.com/paper/2312.12241/) (2023)
- [DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning](https://mlsanity.com/paper/2310.15205/) (2023)
- [Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors](https://mlsanity.com/paper/2412.09416/) (2024)
- [A Survey of Useful LLM Evaluation](https://mlsanity.com/paper/2406.00936/) (2024)
- [Multimodality of AI for Education: Towards Artificial General Intelligence](https://mlsanity.com/paper/2312.06037/) (2023)
- [Towards Modeling Learner Performance with Large Language Models](https://mlsanity.com/paper/2403.14661/) (2024)
- [CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracer](https://mlsanity.com/paper/2406.10296/) (2024)
- [Assessing Student Errors in Experimentation Using Artificial Intelligence and Large Language Models: A Comparative Study with Human Raters](https://mlsanity.com/paper/2308.06088/) (2023)
- [Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Education](https://mlsanity.com/paper/2401.00832/) (2024)
- [TeachLM: Post-Training LLMs for Education Using Authentic Learning Data](https://mlsanity.com/paper/2510.05087/) (2025)
- [OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale](https://mlsanity.com/paper/2602.18832/) (2026)
- [StuGPTViz: A Visual Analytics Approach to Understand Student-ChatGPT Interactions](https://mlsanity.com/paper/2407.12423/) (2024)
- [FOKE: A Personalized and Explainable Education Framework Integrating Foundation Models, Knowledge Graphs, and Prompt Engineering](https://mlsanity.com/paper/2405.03734/) (2024)
- [Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models](https://mlsanity.com/paper/2408.10947/) (2024)
- [Evaluating Large Language Models on the GMAT: Implications for the Future of Business Education](https://mlsanity.com/paper/2401.02985/) (2024)
- [Helpful or Harmful? Exploring the Efficacy of Large Language Models for Online Grooming Prevention](https://mlsanity.com/paper/2403.09795/) (2024)
- [When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Community](https://mlsanity.com/paper/2602.14477/) (2026)
- [AI Chatbots as Multi-Role Pedagogical Agents: Transforming Engagement in CS Education](https://mlsanity.com/paper/2308.03992/) (2023)
- [When Generative AI Meets Workplace Learning: Creating A Realistic & Motivating Learning Experience With A Generative PCA](https://mlsanity.com/paper/2405.15561/) (2024)
- [Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions](https://mlsanity.com/paper/2504.15918/) (2025)
- [Validating the Effectiveness of a Large Language Model-based Approach for Identifying Children's Development across Various Free Play Settings in Kindergarten](https://mlsanity.com/paper/2505.03369/) (2025)
- [When AI Agents Learn from Each Other: Insights from Emergent AI Agent Communities on OpenClaw for Human-AI Partnership in Education](https://mlsanity.com/paper/2603.16663/) (2026)
- [A Scoping Review of Large Language Model-Based Pedagogical Agents](https://mlsanity.com/paper/2604.12253/) (2026)
- [Embrace Opportunities and Face Challenges: Using ChatGPT in Undergraduate Students' Collaborative Interdisciplinary Learning](https://mlsanity.com/paper/2305.18616/) (2023)
- [Quantifying Divergence for Human-AI Collaboration and Cognitive Trust](https://mlsanity.com/paper/2312.08722/) (2023)
- [Making a Long Story Short in Conversation Modeling](https://mlsanity.com/paper/2402.00143/) (2024)
- [The Advancement of Personalized Learning Potentially Accelerated by Generative AI](https://mlsanity.com/paper/2412.00691/) (2024)
- [Exploring Artificial Intelligence Tutor Teammate Adaptability to Harness Discovery Curiosity and Promote Learning in the Context of Interactive Molecular Dynamics](https://mlsanity.com/paper/2506.22520/) (2025)

## Abstract (arXiv)

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