Photo shot in summer 2019.

[Twitter] [Google Scholar] [Github] [LinkedIn]

[MIT Website]


Hi, I am a Ph.D. student at MIT Media Lab, advised by Professor Deb Roy. I am affiliated with Center for Constructive Communication, formerly known as Laboratory for Social Machines (LSM). My research interests lie at the intersection of Natural Language Processing (NLP) and Human Communication, with a focus on enhancing both human-computer interaction and human-human communication.

#AI4Comm #NLP: I develop novel methods to align Large Language Models (LLMs) with humans to improve the efficacy of Human-AI Interaction (HAI). Additionally, I draw upon social sciences and cognitive science to identify techniques that could enable constructive human-human communication with the help of AI. Ultimately, my research aims to develop AI systems that can facilitate effective and meaningful communication between humans and between humans and machines.

Previously, I graduated with M.S. in Symbolic Systems from Stanford University, where I was fortunate to be advised by Professor Michael C. Frank. At Stanford, I worked as a teaching assistant in CS224N Natural Language Processing with Deep Learning for Professor Christopher Manning. I also TA-ed and participated in developing Stanford first NLP + Ethics class CS384 Ethical and Social Issues in NLP for Professor Dan Jurafsky. Besides, I was affiliated with the following groups: Stanford Language and Cognition Lab, Stanford Natural Language Processing Group, Stanford Machine Learning Group.

Before Stanford, I spent 4 years as an undergraduate in Computer Science and Linguistics at Emory University, where I worked with Jinho D. Choi in Emory NLP Lab on natural language processing.

Don't hesitate to email me if you are interested in research opportunities or want to collaborate. I constantly mentor undergrad and grad students from MIT, Harvard, and other schools.



(* indicate equal contribution)

ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings
William Brannon, Suyash Fulay, Hang Jiang, Wonjune Kang, Brandon Roy, Jad Kabbara, and Deb Roy
arXiv 2023
[arXiv] [Code]

PersonaLLM: Investigating the Ability of GPT-3.5 to Express Personality Traits and Gender Differences
Hang Jiang, Xiajie Zhang, Xubo Cao, and Jad Kabbara
IC2S2 2023
[arXiv] [Code] [Slides]
Covered by [Science]

CommunityLM: Probing Partisan Worldviews from Language Models
Hang Jiang, Doug Beeferman, Brandon Roy, and Deb Roy
[Paper] [arXiv] [Code] [Video] [Slides] [Poster] [Models]

Exploring Time Trends and Public Opinions on COVID-19-related Therapeutics on Twitter
Yining Hua*, Hang Jiang*, Shixu Lin, Jie Yang, Joseph M. Plasek, David W. Bates, and Li Zhou
JAMIA 2022
[Paper] [arXiv] [Code]

Contrastive Learning of Medical Visual Representations from Paired Images and Text
Yuhao Zhang*, Hang Jiang*, Yasuhide Miura, Christopher D. Manning, and Curtis P. Langlotz
MLHC 2022
[Paper] [OpenReview] [arXiv] [Video]

Exploring Patterns of Stability and Change in Caregivers' Word Usage Across Early Childhood
Hang Jiang, Michael C. Frank, Vivek Kulkarni, and Abdellah Fourtassi
Cognitive Science 2022
[Paper] [PsyArXiv] [Code]

Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis
Hang Jiang*, Yining Hua*, Doug Beeferman, and Deb Roy
LREC 2022
[Paper] [arXiv] [Code] [Slides] [Poster] [Video]

Topic-time Heatmaps for Human-in-the-loop Topic Detection and Tracking
Doug Beeferman, and Hang Jiang
KDD 2021, Workshop on Data Science with Human in the Loop
[Paper] [arXiv]

LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking
Hang Jiang*, Sairam Gurajada*, Qiuhao Lu, Sumit Neelam, Lucian Popa, Prithviraj Sen, Yunyao Li, Alexander Gray
ACL 2021
[Paper] [arXiv] [Code] [Slides] [Video]
Oral Presentation

Automatic Text-based Personality Recognition on Monologues and Multiparty Dialogues Using Attentive Networks and Contextual Embeddings
Hang Jiang, Xianzhe Zhang, and Jinho D. Choi
AAAI 2020, Student Abstract and Poster Program
[Paper] [arXiv] [Code] [Data] [Poster] [Slide]
Spotlight Presentation

DialectGram: Detecting Dialectal Variation at Multiple Geographic Resolutions
Hang Jiang*, Haoshen Hong*, Yuxing Chen*, and Vivek Kulkarni
SCiL 2020
[Project] [Paper] [arXiv] [Code] [Demo] [Data] [Slides]
Oral Presentation

Selected Honors