Exploring the Design of LLM-Powered Question Generation for Deaf and Hard of Hearing Learners

Si Chen, Shuxu Huffman, Qingxiaoyang Zhu, Haotian Su, Qi Wang, & Raja Kushalnagar (2026) designed and evaluated an LLM-powered question-generation system tailored to Deaf and Hard of Hearing (DHH) learners for video-based learning. The study uses Language Deprivation Theory to uncover risks in learner–LLM interactions and derive design implications.

Key Findings

• Two novel question strategies: Beyond baseline questions generated directly from a video transcript, the system introduces Visual Questions (identifying video timestamps where visual information is likely to be misinterpreted — rapid movements, misaligned captions, dense on-screen text) and Emotion Questions (identifying timestamps where prior DHH learners shared emotional reactions, such as frustration or confusion, captured via facial-expression analysis).
• Three-phase pipeline: Stage 1 generates baseline questions with GPT-3.5; Stage 2 incorporates DHH learner data (emotion and visual) to target overlooked learning moments; Stage 3 iteratively refines questions with DHH students and instructors for linguistic accessibility (simpler sentence structures, closed formats like multiple-choice and true/false). The final mini question bank contained 30 questions (10 per strategy).
• User study (N=16): The prototype generally improved Self Efficacy (M=5.70, SD=1.12 on a 7-point scale). Base questions excelled at connecting text and image and understanding concepts; emotion questions raised awareness of shared difficulties; visual questions were valued more by Deaf than Hard-of-Hearing participants.
• The accessibility gap: LLMs struggle because text-based prompts are mismatched with DHH learners' sign-based first/native languages. Unnecessary linguistic complexity (compound sentences, double negatives) increases cognitive load and confusion.
• Deaf vs. HoH differences: Deaf participants selected visual questions more than HoH learners, who reported fast caption-reading speed and less need for visual support.

Implications for AI in Education

The study highlights the importance of considering language diversity and culture in the design of LLM-based educational technology. LLMs offer significant potential for personalized and automated question generation at scale, but they risk encoding technology bias against users whose first language is not spoken language. The design-based approach — layering learner-specific data into generation and iteratively revising with the target community — offers a template for equitable Special Education tooling, grounded in Universal Design for Learning, that centers the users' own language and experience rather than treating accessibility as an afterthought.

Connected Concepts

• LLM
• Generative AI
• Special Education
• Inclusive Learning
• Automated Question Generation
• Personalized Learning
• Equity In AI Education
• Student Experience
• Universal Design For Learning
• Self Efficacy
• Language Learning
• Bias Mitigation
• Cognitive Offloading
• Neurodiversity

Connected Articles

• GenAI Minoritized Knowledges Disability — Generative AI and the marginalization of minoritized knowledges: the case of disability
• Dyslexlens Dyslexic Learners AI — DysLexLens: A Low-Resource LLM Framework for Analysing Dyslexic Learners
• Slidesqaqa Pedagogical Question Generation — SlideQAQA: Pedagogical Question Generation
• Generate Then Validate Question Gen — Generate-then-validate question generation
• Kt4eqg Personalized Question Generation — KT4EQG: Personalized Question Generation

Citation

Chen, S., Huffman, S., Zhu, Q., Su, H., Wang, Q., & Kushalnagar, R. (2026). Exploring the design of LLM-powered question generation for deaf and hard of hearing learners. Computers and Education: Artificial Intelligence, 10, 100615.