Xiaolei Huang Homepage

We have released a Twitter dataset of COVID-19 with automatically annotated entities (keywords and location)

Brief Intro.

I'm a UMRF Ventures Research assistant professor at University of Memphis. I obtained Ph.D. in Information Science (advised by Dr. Michael J. Paul and Prof. Robin Burke) @ the University of Colorado Boulder. My current research interest is in trustworthy NLP, model robustness, & large language model (LLM), with applications in health informatics & LLM for Sciences.

Email me with your CV and Transcripts if you plan to work with me.

I am looking for two PhD students for the 2026 Spring and Fall. A student with an MS degree or research experience is preferred.

We have acquired VR and robotic devices (drones and vehicles)!

See my [CV] (07-23-2025), The reference list is based on request.

Paid research projects for undergraduate students are available via NSF REU. Please email me with your CV and unofficial transcripts. US citizen or permanent residents are required.

The current two REU positions are fulfilled.

Top 5 News:

2025 - 08
- We have two papers accepted by the EMNLP-25
  - Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation
  - Bhaasha, Bhāṣā, Zaban: A Survey for Low-Resourced Languages in South Asia – Current Stage and Challenges
- Our HBCU-EiR project has been awarded by NSF. We will develop robust multimodal LLMs and applications for health and business fields.
2025 - 06
- I have received the NSF CAREER!
- Our study "Joint Imbalance Adaptation for Radiology Report Generation" (Impact Factor: 5.4) has been published in Journal of Health Informatics Research.
- Our literature review on synthetic data generation is available online, "A Scoping Review of Synthetic Data Generation for Biomedical Research and Applications"

Old News

2025 - 05
- We have received an NSF travel grant [Link] to support student researchers to present at the IEEE ICHI-25.
2025 - 04
- My REU student Mayira won the best Undergraduate Presentation award (the iTiger Computing Services for Multidisciplinary Research Communities) in our Annual Research Day.
- I will serve an NSF panel after resuming from a break in February. I will serve on NSF panels (2).
2025 - 03 We have a collaborative study with St Jude Children's Hospital, NLP for cancer survivors.
2025 - 01
- Our paper "Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts" has been accepted by NAACL-25, 1st-authored by my PhD student Weisi Liu.
- Our imbalance effects on clinical large language model is accepted by the ICHI-25, which is 1st-authored by an undergraduate (supported by NSF REU).
2024 - 12 My efforts in AI and Cyberinfrastructure has been covered by the Memphis Business Journal.
2024 - 11
- I received a grant from ACRE to extend my research of LLMs for Agricultural Engineering.
- I will serve an NSF panel in 2025.
2024 - 10 We will organize a workshop of Trustworthy LLMs for regional collaborators from both academia and industry.
2024 - 09 I will serve in an NSF panel.
2024 - 08 I am assisting organizing IEEE ICHI 2025, please consider submitting your valuable manuscripts.
2024 - 07 Our paper "Time Matters: Examine Temporal Effects on Biomedical Language Models" has been accepted at AMIA-24.
2024 - 06 Our ICHI-24 paper (Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts) won the best paper award!
2024 - 06 I have received an NSF award (LINK).
2024 - 06 Our project has been awarded by NAIRR Pilot Program (NAIRR240165) with GPU and other computational resource allocations.
2024 - 05 I have received a research grant to build multimodal LLM for human-robot interactions with applications in transportation, health, and agriculture.
2024 - 04 I gave a talk at the IIS Cognitive Science Seminar about our recent ICHI-24 work, here is the slides.
2024 - 03
- Our paper "Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts" has been accepted at ICHI-24.
- My undergraduate mentees Hema and Precious won the research award in our annual Research Symposium for their imbalance learning project.
- I will serve in NSF panel(s).
- My undergraduate mentee Hema has won Experiential Learning Fellowship for our imbalance learning project.
2023 - 12 I will serve in an NSF panel in 2024.
2023 - 11
- A collaborative work with St Jude Children's Research Hospital, Natural Language Processing with Machine Learning Methods to Analyze Unstructured Patient-Reported Outcomes Derived from Electronic Health Records: A Systematic Review, has been accepted by Artificial Intelligence In Medicine. [LINK]
- I will serve in an NSF panel.
- I have received an internal research grant ($5K) to strengthen AI computing and security services.
- My student Weisi received the Neathery Fellowship, only 1 among newly enrolled graduate students.
- I gave a remote talk at the Emory University.
2023 - 10 I gave an invited talk of "Towards Trustworthy Natural Language Processing for Biomedical Research" at the Frank M. Norfleet Forum for regional biomedical researchers. [LINK]
2023 - 09 I have received an NSF award to acquire a GPU cluster for the whole Mid-South / Delta Region (LINK) aiming to advance regional deep learning research and education.
2023 - 06 I have received an NSF REU supplement. If you are an undergraduate student, feel free to drop me an email.
2023 - 04 Our paper "Token Imbalance Adaptation for Radiology Report Generation" has been accepted by Conference on Health, Inference, and Learning (CHIL).
2023 - 03 I have received an NSF award (LINK).
2023 - 02 I will serve in an NSF reviewing panel.
2022 - 11 Community of Research Scholars (CoRS) Award to build trustworthy machine learning.
2022 - 08 Our paper "A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation" has been accepted by Conference on Information and Knowledge Management (CIKM).
2022 - 06 I have received the Ralph E. Powe Junior Faculty Enhancement Award.
2022 - 05 My student Yuexin Wu got her first paper "Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification" accepted at *SEM 2022.
2022 - 04 Our Paper "Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification" has been accepted by NAACL 2022.
2022 - 04 Our Paper "Learning to Adapt Domain Shifts of Moral Values via Instance Weighting" has been accepted by HyperText 2022.
2022 - 03 Our paper "Enriching Unsupervised User Embedding via Medical Concepts" has been accepted by Conference on Health, Inference, and Learning (CHIL).
2022 - 02 I will serve in an NSF reviewing panel.
2022 - 01 I have received an award from West Cancer Foundation to promote health equity. Thanks!
2022 - 01 Our paper "Twitter and Facebook posts about COVID-19 are less likely to spread misinformation compared to other health topics" has been accepted by PLOS ONE.
2021 - 12 We will organize User-NLP 2022 colocate with WWW-22 online~ Please consider submitting your paper.
2021 - 10 Community of Research Scholars (CoRS) Award from the University of Memphis.
2021 - 09 I have received a research gift from Adobe Research * 4 times. Thanks!
2021 - 02 Paper of "User Factor Adaptation for User Embedding via Multitask Learning" was accepted by Adapt-NLP 2021.
2020 - 11 I have successfully defended my dissertation, Metadata Matters: Adaptation Methods for Robust Document Classification. [Thesis Link]
2020 - 10 I will join University of Memphis, Department of Computer Science as an assistant professor starting in Jan 2021.
2020 - 06 I have won Outstanding Research Assistant Award (AY 19-20) at the University of Colorado Boulder.
2020 - 05 I will join Amazon Lab 126 as a (remote) summer intern.
2020 - 04 We have released a Twitter dataset of COVID-19 with automatically annotated entities (keywords and location). We keep updating the data.
2020 - 02 Paper of "Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition" was accepted by LREC 2020.
2020 - 01 Visiting Johns Hopkins University. Hosted by Prof. Mark Dredze. Hope to have collaborations in health related projects.

Press Coverage

New local supercomputer cluster aims to ‘bridge’ industry, research, The Business Journal, by Cole Schnell, 12-13-2024
Does TikTok push graphic content onto its users?, The Daily Helmsman, by Chloe Brannon, 04-26-2022.
Closing the Spaces in the U.S. Healthcare Gap, The MITRE, by Karina Wright, 10-05-2022.
New study investigates early claims of COVID-19 ‘infodemic’, The Hill, by Brooke Migdon, 01-12-2022.
Credible COVID-19 social media posts more common than misinformation, The GW Hatchet, by Jackson Lanzer, 01-24-2022.
Online Pandemic Fretting Has a Public Health Upside, Medical Daily, by Maureen Salamon, 11-20-2020.

Data Announcement

A sentiment analysis dataset that contains user demographic information (gender and age) that could potentially be used for author-level debiasing and fairness evaluation. Over 1 M documents & 800K user entries.
A COVID-19 Twitter dataset.
- Dataset: https://doi.org/10.5281/zenodo.3735015
- Documentation: http://twitterdata.covid19dataresources.org/index

Acknowledgement

past

ORAU, Adobe, West Cancer F.

Google Sites

Report abuse