Independent Research Project – Self and Introspection in Large Language Models
Published:
Exploratory project investigating the role of self-referential processing in introspective awareness in LLMs using probing and steering techniques.
Research
Mapping LLM decision-making in computational psychiatry parameter space
Published:
Rotation project characterising LLM behaviour on canonical decision-making tasks from computational psychiatry, and locating model behaviour within the parameter space of standard cognitive models.
Cognitive alignment between humans and LLMs in a memory foraging task
Published:
MSc thesis project investigating whether large language models exhibit human-like search dynamics in a semantic memory foraging task.