Memory Traces: Are Transformers Tulving Machines?
This work addresses the problem of evaluating AI models against psychological theories for researchers in AI and cognitive science, but appears incremental as it applies existing tests to new models.
The paper investigates whether current large language models (LLMs) fully instantiate psychological memory models, specifically Tulving's, by revisiting original Tulving-Watkins tests, but does not report concrete results or numbers.
Memory traces--changes in the memory system that result from the perception and encoding of an event--were measured in pioneering studies by Endel Tulving and Michael J. Watkins in 1975. These and further experiments informed the maturation of Tulving's memory model, from the GAPS (General Abstract Processing System} to the SPI (Serial-Parallel Independent) model. Having current top of the line LLMs revisit the original Tulving-Watkins tests may help in assessing whether foundation models completely instantiate or not this class of psychological models.