COGS560 LARGE LANGUAGE MODELS FOR REASONING AND COGNITION
| Course Code: |
9020560 |
| METU Credit (Theoretical-Laboratory hours/week): |
3(3-0) |
| ECTS Credit: |
7.0 |
| Department: |
Cognitive Sciences |
| Language of Instruction: |
English |
| Level of Study: |
Graduate |
| Course Coordinator: |
|
| Offered Semester: |
Fall and Spring Semesters. |
Course Content
This course explores how large language models (LLMs) represent. process. and generate
information. with a focus on reasoning and cognition. Students will examine the
architectures. learning mechanisms. and emergent abilities of LLMs. and analyze their
reasoning behaviors through cognitive science and computational perspectives. The course
covers theoretical and practical aspects of developing computational models for multi-step
reasoning. and explores capabilities of such models from cognitive aspects such as
compositionality. generalization. biases and human?model comparisons. Through lectures.
research discussions. practical exercises. and a term project. students will develop skills to
build their own specialized reasoning models across tasks and domains. learn methods for
analysis and designing experiments. critically assess model capabilities. and explore
interdisciplinary research questions at the intersection of AI and human cognition.
