Simulating LLM-to-LLM Tutoring for Multilingual Math Feedback
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909639396818944 |
|---|---|
| author | Tonga, Junior Cedric Srivatsa, KV Aditya Maurya, Kaushal Kumar Koto, Fajri Kochmar, Ekaterina |
| author_facet | Tonga, Junior Cedric Srivatsa, KV Aditya Maurya, Kaushal Kumar Koto, Fajri Kochmar, Ekaterina |
| contents | Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them increasingly relevant for AI-assisted education. However, their ability to provide effective instructional support across different languages, especially for mathematically grounded reasoning tasks, remains largely unexamined. In this work, we present the first large-scale simulation of multilingual tutor-student interactions using LLMs. A stronger model plays the role of the tutor, generating feedback in the form of hints, while a weaker model simulates the student. We explore 352 experimental settings across 11 typologically diverse languages, four state-of-the-art LLMs, and multiple prompting strategies to assess whether language-specific feedback leads to measurable learning gains. Our study examines how student input language, teacher feedback language, model choice, and language resource level jointly influence performance. Results show that multilingual hints can significantly improve learning outcomes, particularly in low-resource languages when feedback is aligned with the student's native language. These findings offer practical insights for developing multilingual, LLM-based educational tools that are both effective and inclusive. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04920 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simulating LLM-to-LLM Tutoring for Multilingual Math Feedback Tonga, Junior Cedric Srivatsa, KV Aditya Maurya, Kaushal Kumar Koto, Fajri Kochmar, Ekaterina Computation and Language Artificial Intelligence Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them increasingly relevant for AI-assisted education. However, their ability to provide effective instructional support across different languages, especially for mathematically grounded reasoning tasks, remains largely unexamined. In this work, we present the first large-scale simulation of multilingual tutor-student interactions using LLMs. A stronger model plays the role of the tutor, generating feedback in the form of hints, while a weaker model simulates the student. We explore 352 experimental settings across 11 typologically diverse languages, four state-of-the-art LLMs, and multiple prompting strategies to assess whether language-specific feedback leads to measurable learning gains. Our study examines how student input language, teacher feedback language, model choice, and language resource level jointly influence performance. Results show that multilingual hints can significantly improve learning outcomes, particularly in low-resource languages when feedback is aligned with the student's native language. These findings offer practical insights for developing multilingual, LLM-based educational tools that are both effective and inclusive. |
| title | Simulating LLM-to-LLM Tutoring for Multilingual Math Feedback |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.04920 |