aiqbench analysis
This arXiv preprint describes a retrieval-augmented generation (RAG) tutor that answers student questions posed in Mandarin, returns bilingual responses, and produces technical-term glossaries. On 91 Piazza posts, the authors report 83.52% correct and helpful answers, 76.92% high-quality translations, and glossaries for 64.47% of questions. These are single-course, self-reported results on a small sample, so they indicate promise rather than established effectiveness. The main open questions are how well the approach generalizes to other courses and languages, and how it compares with human teaching assistants.
Multi-sourced AI Tutor for Non-Native English Speaker Students
arXiv:2610.22163v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being adopted as teaching tools in computing education, particularly for developing AI tutors capable of answering student questions. With the rise in enrollment of international students in computing programs, researchers have begun to explore the difficulties that non-native English speaker (NNES) students face in computing courses due to language barriers. To aid such students, we developed a general-purpose AI tutor system that can process student questions in foreign languages (currently focused on Mandarin) and provide bilingual responses. Our system also incorporates the functionality of generating a glossary of technical terms and their explanations to enhance comprehension. Our approach utilizes a specialized Retrieval-Augmented Generation (RAG) pipeline with a novel question extraction mechanism, enabling us to effectively utilize a diverse array of course materials for answering student queries. We evaluated our AI tutor using 91 Piazza posts, demonstrating that it could answer 83.52% of the posts correctly and in a helpful manner. The tutor also provided high-quality translations for 76.92% of the questions and generated technical term glossaries for 64.47% of them. Our findings underscore the potential of multi-source RAG pipeline in enhancing AI tutor systems, offering support for non-native speakers that are challenging to provide with traditional supporting staff of a computing course.
Abstract:Large language models (LLMs) are increasingly being adopted as teaching tools in computing education, particularly for developing AI tutors capable of answering student questions. With the rise in enrollment of international students in computing programs, researchers have begun to explore the difficulties that non-native English speaker (NNES) students face in computing courses due to language barriers. To aid such students, we developed a general-purpose AI tutor system that can process student questions in foreign languages (currently focused on Mandarin) and provide bilingual responses. Our system also incorporates the functionality of generating a glossary of technical terms and their explanations to enhance comprehension. Our approach utilizes a specialized Retrieval-Augmented Generation (RAG) pipeline with a novel question extraction mechanism, enabling us to effectively utilize a diverse array of course materials for answering student queries. We evaluated our AI tutor using 91 Piazza posts, demonstrating that it could answer 83.52% of the posts correctly and in a helpful manner. The tutor also provided high-quality translations for 76.92% of the questions and generated technical term glossaries for 64.47% of them. Our findings underscore the potential of multi-source RAG pipeline in enhancing AI tutor systems, offering support for non-native speakers that are challenging to provide with traditional supporting staff of a computing course.
Artificial Intelligence (cs.AI)
arXiv:2610.22163 [cs.AI]
(or arXiv:2610.22163v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.22163 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 302 words
Related coverage
The Open ASR Leaderboard Adds Its First Global South Language
Hugging Face · Aug 28, 2026
Links #3: 2026/06 Part 1
LessWrong · Jun 15, 2026
The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning
arXiv · Oct 7, 2026
NVIDIA Nemotron 3 Ultra Powers Faster, More Efficient Reasoning for Long-Running Agents
NVIDIA · Jun 4, 2026