Memory GAPS: Would LLMs pass the Tulving Test?
This work addresses the problem of understanding memory mechanisms in LLMs for researchers in AI and cognitive science, but it appears incremental as it applies an existing test to a new domain.
The paper investigates whether the Tulving Test, a framework for assessing human memory, can be applied to evaluate memory performance in Large Language Models (LLMs). It explores if this decades-old framework provides insights into how LLMs perform acts of remembering.
The Tulving Test was designed to investigate memory performance in recognition and recall tasks. Its results help assess the relevance of the "Synergistic Ecphory Model" of memory and similar RK paradigms in human performance. This paper starts investigating whether the more than forty-year-old framework sheds some light on LLMs' acts of remembering.