Research
[This site is currently under construction, but here are some bullet points that will be fleshed out]:
Broadly speaking, I am interested in the intersection of computational linguistics and psycholinguistics, with the long-term goal of formally characterizing human and machine intelligence, specifically language capabilities. I have been exploring various research topics, including:
- Properties of cognitively / neurally plausible computational models of sentence-level language processing and production;
- Models / Frameworks: gradient symbolic computation, self-organized sentence processing, dynamic-field theory, ACT-R, etc.
- Behavioral and algorithmic levels understanding of large language models (LLMs):
- targeted evaluations on the extent to with LLMs align with human linguistic behaviors;
- understanding in-context learning and forward-pass, layer-time dynamics;
- mechanistic interpretations on how LLMs form sentence-level syntactic representations;
- linguistic generalization ability with training data manipulation;
- Psycholinguistic experiments on Tree-Adjoining Grammar (TAG) based sentence production theories.