Singapore

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.

AAAI 2026

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

distractor generative ai k-12 ai education multi-choice question

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". 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 need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

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.

To access this event page, you need to log in with the **email address you registered with**. 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.

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

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.

GRAFT: Graph-Augmented Framework with Vision Transformers for Multi-Label Classification

As populations age globally, it is increasingly important to develop digital tools for assessing the functional ability of older adults at scale. This study explores the potential for using movement data from exergaming interventions recorded with wearable inertial measurement units (IMUs) to predict fall risk in older adults. We propose a self-supervised learning approach that uses Long Short-Term Memory (LSTM) architectures to analyze exergaming signals and gait patterns. Two models are evaluated: (i) a baseline supervised LSTM classifier and (ii) an LSTM-based autoencoder that learns latent representations of movement dynamics. These latent embeddings not only improve fall-risk prediction (F1 = 0.444 versus. 0.233 for the baseline) but also form a foundation for inferring other functional and physiological measures in the future. Using data from a 14-week exergaming intervention with 36 participants, our findings demonstrate that unsupervised representations derived from movement signatures during tasks like exergames can encode clinically relevant markers of physical ability. The use of low-cost IMU sensors to record movement data coupled with artificial intelligence-based data processing enables scalable and continuous fall risk prediction among older adults undergoing exercise-based interventions for improving functional ability.

A Self-Supervised Learning-Based Approach to Predict Fall Risk in Older Adults from Exergaming Intervention Movements

Brain-Computer Interfaces (BCIs) have emerged as alternative 
means of communication for individuals with speech & motor 
impairments. These systems enable patients to express themselves without any articulation, by decoding speech from neural activity. However, most of the existing studies rely on invasive surgical procedures, with limited studies using non-invasive signals for phoneme or word level classification, thus covering a short vocabulary. To the best of our knowledge, this study presents the first demonstration of a framework for sentence level imagined speech synthesis from non-invasive electroencephalography (EEG) signals. Our model uses an Efficient-Net based masked auto-encoder approach for learning feature embeddings from EEG signals which are then used for fine-tuning BERT for next token generation. For this study, Large Spanish Speech EEG Dataset has been used with a mixed subject approach for both training & evaluation purposes, resulting into a 48.92% accuracy.

Towards Sentence Level Imagined Speech Generation from EEG signals

Loneliness is a major determinant of poor health and wellbeing in older adults, yet existing interventions remain limited in accessibility, personalisation, and long-term effectiveness. Emerging technologies, including artificial intelligence (AI) and virtual reality (VR), offer new opportunities for emotionally adaptive and engaging support. This study explores how older adults perceive the potential of VR to address loneliness through a participatory focus group and interactive VR workshop. Thematic analysis revealed that participants sought technologies fostering agency, emotional regulation, and meaningful social connection, rather than existing strategies of passive distraction. We present several AI integration approaches that can actualise participants’ visions of effective loneliness support, augmenting the therapeutic capabilities of immersive technologies. These findings highlight the promise of AI-enhanced and ethically grounded VR interventions as tools for emotional growth and healthy ageing, emphasising the importance of co-design and user-centred development in future digital therapeutics for loneliness.

From Isolation to Connection: Participatory Insights on AI and VR for Healthy Ageing

This work addresses the large inter-individual variability in physiological adaptation to exercise, which limits the effectiveness of generalized programs. We introduce mechanobioAI, a knowledge-graph framework that operationalizes mechanobiology to infer adaptive predispositions and generate N-of-1, parameterized exercise prescriptions. The framework links observable performance variables such as strength, velocity, and recovery to latent mechanobiological traits including muscle–tendon stiffness, fiber-type composition, and recovery kinetics. Estimated predispositions are integrated with a quantitative model of the titin-kinase mechanosensitive switch to prescribe mechanical dosages—load, volume, frequency, and tempo—targeting specific molecular pathways. Beyond dosage, the knowledge graph also constrains exercise selection so that chosen movements instantiate the intended mechanical stimuli, aligning program design with user goals. 

By encoding mechanobiological and genetic principles directly within a knowledge graph, mechanobioAI moves beyond proxy-based AI personalization toward biologically grounded, mechanism-informed coaching. Preliminary feasibility analyses using public datasets that couple anthropometrics and performance proxies with common polymorphisms suggest that graph-inferred traits can recapitulate known genotype–phenotype links. Practically, this approach seeks to increase the speed and magnitude of beneficial adaptation, reduce injury risk through better control of mechanical exposure, and address the lack of principled personalization in current digital fitness tools. The result is a coherent pathway from cellular mechanisms to individualized training programs, enabling scalable N-of-1 prescriptions that are both interpretable and actionable.

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

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads