I am an incoming tenure-track assistant professor in the Luddy School of Informatics, Computing and Engieering at Indiana University. My research focuses on natural language processing and computational linguistics.
Humans rely heavily on implied meaning in everyday communication. I am deeply interested in identifying the first principle that would enable machines, particularly LLMs, to understand the implied meaning of human language. In my research, I have explored ideas from statistical learning theory, linguistics, and cognitive science to help statistical models better capture (definitely not understand!) the pragmatic cues of human language. However, none of these perspectives has yet provided a fully satisfactory answer. I am still actively searching for one.
- Pragmatic Inference: Developing inference approaches that enable LLMs to perform contextual grounding and predict implicatures in human communication.
- Machine Morality: Studying how LLMs can acquire intrinsic morality, resolve moral dilemmas, and achieve human-level moral competence.
- Commonsense Reasoning: Investigating how LLMs can estimate the consequences of verbal actions and behaviors, and acquire commonsense grounded in human social life.
To the best of our knowledge, these are the first generalized moral reasoning models. Huge thanks to all of my collaborators for their contributions and support throughout this project.
Openings: I am looking for self-motivated PhD students for Spring/Fall 2027. Please email me your CV, transcripts, and TOEFL/IELTS scores at liugua@iu.edu. Students with backgrounds in mathematics/statistics, linguistics and cognitive science are also welcome to contact me.
What's new?
- May 2026: Just submitted my meta-review for ACL ARR March. I’m really excited to see so many submissions in the area of moral reasoning. For a long time, only a small number of researchers were working on it.
- May 2026: I will serve as an area chair for ACL ARR May and EMNLP2026.
- May 2026: Extremely excited to enjoy the summer together with Dr. Bocheng Chen from University of Mississippi and Dr. Zoe Xi Chen from Nanyang Technological University on a new computational pragmatics framework for toxic language and malicious attack commands.
- May 2026: Start to work together with Dong Duong and An Pham on a project about the shallow heuristics in code models.
- May 2026: Gave a talk titled From Language Models to Moral Machines at Capital One.
- April 2026: Han Zi has joined my lab to study pragmatic gaps in moral alignment.
- March 2026: Gave a talk titled From Language Models to Moral Machines at IU Indianapolis.
Lab
I am the PI of the Language and Social Intelligence Lab at Indiana University. Our ultimate goal is to enable machines to understand human language and develop social intelligence that supports people.
Prospective students
I am actively seeking motivated Ph.D. students and research interns. If you are interested in joining the lab, please feel free to email me a brief introduction along with your CV. If you are a student at Indiana University, you are also welcome to stop by my office at IT555.
Current Members
I am extremely fortunate to work with:- Han Zi — incoming Ph.D. student (Masters: Northeastern University; Bachelor: University of Electronic Science and Technology of China)
- Dong Duong — Undegraduate Researcher at Michigan State University
- An Pham — Undegraduate Researcher at Michigan State University