Singapore

Educational question generation (EQG) is a crucial
component of intelligent educational systems, significantly
aiding self-assessment, active learning, and personalized
education. While EQG systems have emerged, existing
datasets typically rely on predefined, carefully edited
texts, failing to represent real-world classroom content,
including lecture speech with a set of complementary
slides. To bridge this gap, we collect a dataset of
educational questions based on lectures from real-world
classrooms. On this realistic dataset, we find that current
methods for EQG struggle with accurately generating
questions from educational videos, particularly in aligning
with specific timestamps and target answers. Common
challenges include selecting informative contexts from
extensive transcripts and ensuring generated questions
meaningfully incorporate the target answer. To address the
challenges, we introduce a novel framework utilizing large
language models (LLMs) for dynamically selecting and
rewriting contexts based on target timestamps and answers
in lecture videos. First, our framework selects contexts
from both lecture transcripts and video keyframes based on
answer relevance and temporal proximity. Then, we integrate
the contexts selected from both modalities and rewrite them
into answer-containing knowledge statements, to enhance the
logical connection between the contexts and the desired
answer. This approach significantly improves the quality
and relevance of the generated questions.

AAAI 2026

Context Selection and Rewriting for Video-based Educational Question Generation

applications

large language models

question generation

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2021

technical paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

As Artificial Intelligence (AI) becomes increasingly integrated into daily life, there is a growing need to equip the next generation with the ability to apply, interact with, evaluate, and collaborate with AI systems responsibly. Prior research highlights the urgent demand from K-12 educators for resources to teach students the ethical and effective use of AI in learning. To address this need, we designed an Large-Language Model (LLM)-based
module to teach prompt literacy. It includes scenario-based deliberate practice activities with direct interaction with intelligent LLM agents, aiming to foster secondary school students' responsible engagement with AI chatbots. We conducted two iterations of classroom deployment in 11 authentic secondary education classrooms, and evaluated 1) AI-based auto-grader's capability; 2) students' performance and attitude changes towards using AI for learning; and 3) the quality of learning and assessment materials. Results indicate that this AI-based auto-grader can perform grading
with satisfactory quality. In addition, the instructional materials supported learners in improving their prompting skills through practice and led to positive shifts in their perceptions of using AI for learning. Furthermore, data from Study 1 informed assessment revisions in Study 2. Analyses of item difficulty and discrimination showed that True/False and open-ended questions more effectively measured prompting literacy than multiple-choice questions for our target learners. These promising outcomes highlight the potential for broader deployment and underscore the need for future large-scale studies to further evaluate learning effectiveness and refine assessment design.

Learning to Use AI for Learning: Teaching Responsible Use of AI Chatbot to K-12 Students Through an AI Literacy Module

Artificial intelligence offers powerful methods for audio
processing and analysis but complex workflows and required
programming skills often limit access for students and
domain experts like marine bioacousticians and soundscape
ecologists. We present an application “Sound-AI”, a code
free and interactive tool that lowers these barriers by
providing users to construct and explore complete AI
pipeline for audio data analysis. Starting from raw
recordings, users can choose from various feature
extraction techniques (MFCC, OpenL3), apply dimensionality
reduction method (PCA, t-SNE, UMAP), and optionally perform
unsupervised clustering (K-Means, GMM, DBSCAN). The results
are displayed in an interactive 2D visualization where user
can compare multiple plots by varying multiple techniques
i.e. t-SNE vs PCA. Interactive plots allow selection of
points or clusters of interest, visualize spectrograms in
desired frequency range, and play audio clip of associated
points. An integrated ‘Help’ feature provides explanation
of each method (i.e. what it is, how it works and practical
use in different domains like bioacoustics), fostering both
conceptual understanding and practical skill. For
precomputed features or embeddings, this tool also supports
training and evaluating various machine learning algorithms
with visual feedback. By merging accessibility,
interactivity, pedagogy, and domain relevance, “Sound-AI”
demystifies AI methods for interdisciplinary education and
supporting research in audio analysis.

Sound-AI: A Pedagogical Tool for Exploring AI in Audio and Bioacoustic Research

This paper considers the development of an AI-based
provably-correct mathematical proof tutor. While Large
Language Models (LLMs) allow seamless communication in
natural language, they are error prone. Theorem provers
such as Lean allow for provable-correctness, but these are
hard for students to learn. We present a proof-of-concept
system (LeanTutor) by combining the complementary strengths
of LLMs and theorem provers. LeanTutor is composed of three
modules: (i) an autoformalizer/proof-checker, (ii) a
next-step generator, and (iii) a natural language feedback
generator. To evaluate the system, we introduce PeanoBench,
a dataset of 371 Peano Arithmetic proofs in human-written
natural language and formal language, derived from the
Natural Numbers Game.

LeanTutor: Towards a Verified AI Mathematical Proof Tutor

Multiple-choice questions (MCQs) are central to instruction and assessment, with distractors revealing student understanding and misconceptions. However, creating high-quality distractors is time-consuming, especially for emerging domains like K–12 AI education. This study explores using generative AI to support distractor creation in a self-paced online module integrating AI and Algebra 1. Five MCQs were selected to compare distractors written by human developers and ChatGPT, using expert reviews and log data from 80 students. Experts rated human distractors higher overall, though AI ones consistently ranked second. Log analysis showed human distractors drew more initial selections, while students who chose AI distractors spent more time engaging without differences in hint use or revisits. Transition patterns across attempts suggest AI-generated distractors can effectively guide students toward correct answers, highlighting their potential for scalable MCQ design.

Brains vs. Algorithms? How Experts and Students See AI-Generated Distractors

Large Language Models (LLMs) have shown immense potential
in education, automating tasks like quiz generation and
content summarization. However, generating effective
presentation slides introduces unique challenges due to the
complexity of multimodal content creation and the need for
precise, domain-specific information. Existing LLM-based
solutions often fail to produce reliable and informative
outputs, limiting their educational value. To address these
limitations, we introduce SlideBot - a modular, multi-agent
slide generation framework that integrates LLMs with
retrieval, structured planning, and code generation.
SlideBot is organized around three pillars:
informativeness, ensuring deep and contextually grounded
content; reliability, achieved by incorporating external
sources through retrieval; and practicality, which enables
customization and iterative feedback through instructor
collaboration. It incorporates evidence-based instructional
design principles from Cognitive Load Theory (CLT) and the
Cognitive Theory of Multimedia Learning (CTML), using
structured planning to manage intrinsic load and consistent
visual macros to reduce extraneous load and enhance
dual-channel learning. Within the system, specialized
agents collaboratively retrieve information, summarize
content, generate figures, and format slides using LATEX,
aligning outputs with instructor preferences through
interactive refinement. Evaluations from domain experts and
students in AI and biomedical education show that SlideBot
consistently enhances conceptual accuracy, clarity, and
instructional value. These findings demonstrate SlideBot’s
potential to streamline slide preparation while ensuring
accuracy, relevance, and adaptability in higher education.

SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations

Many AI-based code assistants, particularly those powered
by Large Language Models (LLMs), provide complete
solutions, which can reduce active problem solving and
limit incidental learning, the acquisition of knowledge as
a byproduct of task engagement. Such learning requires
active participation rather than passive acceptance of
AI-generated answers, which might be incorrect. This study
examines how incidental learning can be supported through
guided interaction. We present LeetCoach, an LLM-assisted
coding platform that applies a cognitive forcing strategy,
prompting learners to reflect and take incremental steps
instead of receiving full solutions. Using LeetCode-style
questions, we conducted a pilot study with novice and
advanced college programmers who completed tasks under
assisted and unassisted conditions. Novices showed
substantial post-test gains despite receiving AI guidance
only during the intervention, suggesting that incidental
exposure improved later performance. Advanced learners
showed smaller gains. Across both groups, participants
required fewer debugging attempts in the post-test compared
to earlier stages, indicating improved debugging efficiency
and algorithmic understanding. These findings provide early
evidence that LLMs can be designed to promote indirect
learning while shaping problem-solving strategies. This
work offers a proof of concept for cognitively informed
tutoring systems in computer science education and
discusses implications for integrating LLMs to enhance both
immediate outcomes and lasting skill development.

How Does LLM-powered Coding Assistance Shape Incidental Learning? Exploring Cognitive Forcing Strategies in Programming Education

Early diagnosis of Alzheimer’s disease (AD) remains a major challenge due to the subtle and temporally irregular progression of structural brain changes in the prodromal stages. Existing deep learning approaches require large longitudinal datasets and often fail to model the temporal continuity and modality irregularities inherent in real-world clinical data. To address these limitations, we propose the Diffusion-Guided Attention Network (DiGAN), which integrates latent diffusion modelling with attention-guided convolutional network. The diffusion model synthesizes realistic longitudinal neuroimaging trajectories from limited training data, enriching temporal context and improving robustness to unevenly spaced visits. The attention-convolutional layer then captures discriminative structural–temporal patterns that distinguish cognitively normal subjects from those with mild cognitive impairment and subjective cognitive decline. Experiments on synthetic and ADNI datasets demonstrate that DiGAN outperforms existing state-of-the-art baselines, showing its potential for early-stage AD detection.

DiGAN: Diffusion-Guided Attention Network for Early Alzheimer’s Disease Detection

Wearable health devices provide continuous, real-time insights into physiological patterns that may reflect underlying systemic diseases. However, validating these signals often requires invasive and costly clinical tests. As the only externally visible microvascular structure, the retina offers a unique noninvasive window into vascular health. Retinal biomarkers including vessel calibers (CRAE, CRVE), arteriovenous ratio (AVR), vessel density, fractal dimension, and tortuosity have been associated with systemic conditions such as diabetes, hypertension, and cardiovascular disease. 
In this study, we leveraged the AIREADI dataset to investigate how retinal vascular features vary across stratified levels of physiological dysregulation, as measured by wearable-derived metrics (e.g., heart rate, $SpO_2$, sleep, activity, and stress scores) collected over 10 days. Participants were categorized into low, moderate, and severe physiological severity groups and further stratified by six chronic disease conditions. 
Our analysis revealed significant associations between higher physiological severity and venular dilation (increased CRVE), reduced arteriovenous ratio (AVR), and elevated venous fractal dimension. These trends were consistent across several disease-specific subgroups, particularly in diabetes, hypertension, and kidney disease. However, parameters such as CRAE and tortuosity showed no consistent or statistically significant changes. 
These findings support the complementary role of retinal imaging and wearable sensors in passive, scalable monitoring of systemic vascular health, offering promise for early risk stratification and precision health interventions.

Integration of Wearable Health Device Data and Retinal Imaging for Multimodal Systemic Disease Stratification

Aging is a major risk factor for multiple chronic diseases, yet individual rates of aging vary significantly. To address the challenge of applying biological age models across populations, this study first harmonized clinical data between the UK Biobank (UKB) and a Chinese cohort (XMUFAH) using statistical distance metrics, selecting 36 health indicators with high distributional similarity. Based on these indicators, a LightGBM biological age prediction model was developed using a UKB population (n=431,113). The model demonstrated strong predictive performance in the independent XMUFAH external validation cohort (n=86,233), confirming its robustness and generalizability for cross-population application. Results show that accelerated biological aging is significantly associated with the future incidence risk of 12 chronic diseases in the UKB cohort and 8 in the XMUFAH cohort, suggesting the model as an effective tool for cross-population assessment of aging and risk prediction for related diseases.

Cross-Cohort Prediction of Biological Age using Routine Medical Examination Data


This paper presents GRAFT (Graph-Augmented Framework with Vision Transformers), a multi-stage framework for multi-label classification of chest X-ray images. GRAFT combines self-supervised vision transformers with graph-based relational learning, designed to enhance prediction accuracy in complex multi-label settings. Our framework operates in three stages: (1) self-supervised pre-training using Masked Autoencoders (MAE) with Vision Transformers to learn robust visual representations without extensive labeled data, (2) multi-perspective graph construction incorporating statistical co-occurrence patterns, spatial relationships, and visual feature similarities to model inter-label dependencies, and (3) uncertainty-weighted fusion through a Contextual Graph Fusion Network (CGFN) that dynamically balances contributions from different graph types, while considering their biomedical contexts. The approach addresses key challenges in multi-label classification, including class imbalance, incomplete annotations, and complex label interdependencies. Given the high prevalence and co-occurrence of thoracic diseases in aging populations, our multi-label framework directly addresses a critical gap in diagnostic care, with implications for healthy aging and longevity. 
We evaluate GRAFT on popular medical imaging datasets.

Downloads

Next from AAAI 2026

Learning to Use AI for Learning: Teaching Responsible Use of AI Chatbot to K-12 Students Through an AI Literacy Module

Similar lecture

EQG-RACE: Examination-Type Question Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

Learning to Use AI for Learning: Teaching Responsible Use of AI Chatbot to K-12 Students Through an AI Literacy Module

Similar lecture

EQG-RACE: Examination-Type Question Generation

Downloads