Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909541604524032 |
|---|---|
| author | Puech, Romain Macina, Jakub Chatain, Julia Sachan, Mrinmaya Kapur, Manu |
| author_facet | Puech, Romain Macina, Jakub Chatain, Julia Sachan, Mrinmaya Kapur, Manu |
| contents | One-to-one tutoring is one of the most efficient methods of teaching. With the growing popularity of Large Language Models (LLMs), there have been efforts to create LLM based conversational tutors which can expand the benefits of one to one tutoring to everyone. However, current LLMs are trained primarily to be helpful assistants and lack crucial pedagogical skills. For example, they often quickly reveal the solution to the student and fail to plan for a richer multi turn pedagogical interaction. To use LLMs in pedagogical settings, they need to be steered to use effective teaching strategies: a problem we introduce as Pedagogical Steering. We develop StratL, an algorithm to optimize LLM prompts and steer it to follow a predefined multi-turn tutoring plan represented as a transition graph. As a case study, we create a prototype tutor for high school math following Productive Failure (PF), an advanced and effective learning design. To validate our approach in a real-world setting, we run a field study with 17 high school students in Singapore and show that StratL succeeds in steering the LLM to follow the PF tutoring strategy. Finally, we highlight challenges in Pedagogical Steering of LLMs and offer opportunities for further improvements by publishing a dataset of PF problems and our code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03781 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure Puech, Romain Macina, Jakub Chatain, Julia Sachan, Mrinmaya Kapur, Manu Human-Computer Interaction Artificial Intelligence Computers and Society Multiagent Systems 97 I.2; H.5; J.4 One-to-one tutoring is one of the most efficient methods of teaching. With the growing popularity of Large Language Models (LLMs), there have been efforts to create LLM based conversational tutors which can expand the benefits of one to one tutoring to everyone. However, current LLMs are trained primarily to be helpful assistants and lack crucial pedagogical skills. For example, they often quickly reveal the solution to the student and fail to plan for a richer multi turn pedagogical interaction. To use LLMs in pedagogical settings, they need to be steered to use effective teaching strategies: a problem we introduce as Pedagogical Steering. We develop StratL, an algorithm to optimize LLM prompts and steer it to follow a predefined multi-turn tutoring plan represented as a transition graph. As a case study, we create a prototype tutor for high school math following Productive Failure (PF), an advanced and effective learning design. To validate our approach in a real-world setting, we run a field study with 17 high school students in Singapore and show that StratL succeeds in steering the LLM to follow the PF tutoring strategy. Finally, we highlight challenges in Pedagogical Steering of LLMs and offer opportunities for further improvements by publishing a dataset of PF problems and our code. |
| title | Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure |
| topic | Human-Computer Interaction Artificial Intelligence Computers and Society Multiagent Systems 97 I.2; H.5; J.4 |
| url | https://arxiv.org/abs/2410.03781 |