Kristin Qi, Youxiang Zhu, Caroline Summerour, John A. Batsis, Xiaohui Liang Early detection of cognitive decline is crucial for enabling interventions that can slow neurodegenerative disease progression. Traditional diagnostic approaches rely on labor-intensive clinical assessments, which are impractical for frequent monitoring. Our pilot study investigates voice assistant systems (VAS) as non-invasive tools for detecting cognitiveContinue reading “Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands”
Author Archives: Xiaohui Liang
Unveil Multi-Picture Descriptions for Multilingual Mild Cognitive Impairment Detection via Contrastive Learning
Kristin Qi, Jiali Cheng, Youxiang Zhu, Hadi Amiri, Xiaohui Liang Detecting Mild Cognitive Impairment from picture descriptions is critical yet challenging, especially in multilingual and multiple picture settings. Prior work has primarily focused on English speakers describing a single picture (e.g., the `Cookie Theft’). The TAUKDIAL-2024 challenge expands this scope by introducing multilingual speakers andContinue reading “Unveil Multi-Picture Descriptions for Multilingual Mild Cognitive Impairment Detection via Contrastive Learning”
Xiaohui gave a talk on “Early Detection of Cognitive Decline Using Voice Assistant”
https://meeting.americangeriatrics.org/about 11:45 AM – 12:45 PM ARTIFICIAL INTELLIGENCE IN AGING RESEARCH AND CLINICAL CARE Room: Grand Hall MN Track: Research CME/CE: 1.0 Sponsored by the Research Committee Moderator: John A. Batsis, MD, FACP, AGSF, FGSA & Kah Poh (Melissa) Loh, MD, MS, This session will focus on emerging research in artificial intelligence and machine learning,Continue reading “Xiaohui gave a talk on “Early Detection of Cognitive Decline Using Voice Assistant””
PhD student Rishank will participate I2SEED program
An Interdisciplinary Training Program in Entrepreneurship and Translational Research for Alzheimer’s Disease and AD-Related Disorders I2SEED is an entrepreneurship focused education program which provides training to help develop and commercialize diagnostic, supportive or therapeutic interventions for Alzheimer’s Disease and AD Related Disorders (ADRD).
Two PhD students will present posters at the New England NLP (NENLP) workshop on April 11, 2025
Focus Directions Make Your Language Models Pay More Attention to Relevant ContextsPresenter: Youxiang Zhu Early Detection of Mild Cognitive Impairment Through Voice Assistant Interactions: An LLM-Driven ApproachPresenter: Kristin Qi New England NLP (NENLP) workshop
Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning (NAACL/CL4Health 2025)
Kristin Qi, Youxiang Zhu, Xiaohui Liang (UMB@PerAnsSumm 2025) We present our approach to the PerAnsSumm Shared Task, which involves perspective span identification and perspective-aware summarization in community question-answering (CQA) threads. For span identification, we adopt ensemble learning that integrates three transformer models through averaging to exploit individual model strengths, achieving an 82.91% F1-score on testContinue reading “Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning (NAACL/CL4Health 2025)”
Adversarial Text Generation using Large Language Models for Dementia Detection (EMNLP 2024)
Youxiang Zhu, Nana Lin, Kiran Sandilya Balivada, Daniel Haehn, Xiaohui Liang Detecting dementia via picture description is a challenging text classification task where powerful Large Language Models (LLMs) have not yet outperformed Pre-trained Language Models (PLMs), with previous studies achieving notable accuracy (>80%). The difficulty lies in the limited explicit features for detection, making itContinue reading “Adversarial Text Generation using Large Language Models for Dementia Detection (EMNLP 2024)”
Exploiting Longitudinal Speech Sessions via Voice Assistant Systems for Early Detection of Cognitive Decline (HealthCom 2024)
Kristin Qi, Jiatong Shi, Caroline Summerour, John Batsis, Xiaohui Liang Mild Cognitive Impairment (MCI) is an early stage of Alzheimer’s disease (AD), a form of neurodegenerative disorder. Early identification of MCI is crucial for delaying its progression through timely interventions. Existing research has demonstrated the feasibility of detecting MCI using speech collected from clinical interviewsContinue reading “Exploiting Longitudinal Speech Sessions via Voice Assistant Systems for Early Detection of Cognitive Decline (HealthCom 2024)”
Exploiting Privacy Preserving Prompt Techniques for Online Large Language Model Usage (GLOBECOM 2024)
Youxiang Zhu, Ning Gao, Xiaohui Liang, and Honggang Zhang Online Large Language Models (LLMs) are widely employed across various tasks, including privacy-sensitive ones like financial advice or paragraph rewriting. Presently, users directly submit prompts to online LLM servers, inadvertently revealing sensitive keywords and facilitating server tracking to build user profiles. In this paper, we proposeContinue reading “Exploiting Privacy Preserving Prompt Techniques for Online Large Language Model Usage (GLOBECOM 2024)”
Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection (INTERSPEECH 2024)
Nana Lin, Youxiang Zhu, Xiaohui Liang, Caroline E Summerour, John A Batsis Mild cognitive impairment (MCI) is a major public health concern due to its high risk of progressing to dementia. This study investigates the potential of detecting MCI with spontaneous voice assistant (VA) commands from 35 older adults in a controlled setting. Specifically, aContinue reading “Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection (INTERSPEECH 2024)”
CogVox 